Scanpy Analysis

%config InlineBackend.figure_formats = ["retina"]  # increase resolution on retina screens
import numpy as np
import pandas as pd
import warnings
import sys
warnings.filterwarnings("ignore")
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))
#import matplotlib as mpl
import matplotlib.pyplot as plt
import matplotlib.colors
import scanpy as sc
import seaborn as sns
import anndata as ad
sc.settings.verbosity = 3             # verbosity: errors (0), warnings (1), info (2), hints (3)
sc.logging.print_header()
sc.settings.n_jobs = 23

scanpy==1.9.1 anndata==0.9.2 umap==0.5.3 numpy==1.23.5 scipy==1.11.1 pandas==1.5.2 scikit-learn==1.3.0 statsmodels==0.14.0 python-igraph==0.10.6 pynndescent==0.5.10

from gtfparse import read_gtf

%load_ext rpy2.ipython

INFO:rpy2.situation:cffi mode is CFFI_MODE.ANY
INFO:rpy2.situation:R home found: /scratch/prj/sangrithi_lab/programs/miniconda3/envs/MS_Conda5/lib/R
INFO:rpy2.situation:R library path: 
INFO:rpy2.situation:LD_LIBRARY_PATH: 
INFO:rpy2.rinterface_lib.embedded:Default options to initialize R: rpy2, --quiet, --no-save
INFO:rpy2.rinterface_lib.embedded:R is already initialized. No need to initialize.

pd.set_option('display.max_columns', 500)
pd.set_option('display.max_rows', 100)#None

plt.rcParams.update({})
# Say, "the default sans-serif font is COMIC SANS"
matplotlib.rcParams['font.sans-serif'] = "Arial"
# Then, "ALWAYS use sans-serif fonts"
matplotlib.rcParams['font.family'] = "sans-serif"
sc.settings.set_figure_params(dpi=125, dpi_save=300, format="pdf", frameon=False)
sc.settings.figdir = '/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Figures/'
# Set context to `"paper"`
sns.set_context("paper", font_scale=1, rc={"font.size":16,"axes.labelsize":16,"axes.titlesize":20})

heatcolors_wr = matplotlib.colors.LinearSegmentedColormap.from_list("", ["white", "#FFF5F0", "#FEE0D2", "#FCBBA1", 
                                                                         "#FC9272", "#FB6A4A", "#EF3B2C", 
                                                                         "#CB181D", "#A50F15", "#67000D"])
heatcolors = matplotlib.colors.LinearSegmentedColormap.from_list("", ["gray", "#000004FF", "#330A5FFF", "#781C6DFF",
                                                                      "#BB3754FF", "#ED6925FF", 
                                                                      "#FCB519FF", "#FCFFA4FF"])

#%%R
#heatcolour_wr <- colorRampPalette(c("white", "#FFF5F0", "#FEE0D2", "#FCBBA1","#FC9272", "#FB6A4A", "#EF3B2C","#CB181D", "#A50F15", "#67000D"))(100)
#show_col(heatcolour_wr)

%%R
require(tidyverse)
require(dplyr)
require(tidyr)
options(mc.cores = 23L)
require(magrittr)
#library(scatterpie)
require(extrafont)
require(scales)
require(viridis)
require(viridisLite)
require(gridExtra)
options(dplyr.width = 200)
#options(repr.matrix.max.cols=500, repr.matrix.max.rows=100)

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: tidyverse

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.2     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.2     ✔ tibble    3.2.1
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.1     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: magrittr

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: 
Attaching package: ‘magrittr’


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: The following object is masked from ‘package:purrr’:

    set_names


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: The following object is masked from ‘package:tidyr’:

    extract


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: extrafont

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Registering fonts with R

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: scales

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: 
Attaching package: ‘scales’


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: The following object is masked from ‘package:purrr’:

    discard


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: The following object is masked from ‘package:readr’:

    col_factor


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: viridis

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: viridisLite

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: 
Attaching package: ‘viridis’


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: The following object is masked from ‘package:scales’:

    viridis_pal


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: Loading required package: gridExtra

WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: 
Attaching package: ‘gridExtra’


WARNING:rpy2.rinterface_lib.callbacks:R[write to console]: The following object is masked from ‘package:dplyr’:

    combine

## Load the Mouse GTF file
gtf_df = read_gtf("/users/k2142342/Lab_Sangrithi/reference/annot/Mus_musculus.GRCm38/Mus_musculus.GRCm38.102.chr.gtf")

INFO:root:Extracted GTF attributes: ['gene_id', 'gene_version', 'gene_name', 'gene_source', 'gene_biotype', 'havana_gene', 'havana_gene_version', 'transcript_id', 'transcript_version', 'transcript_name', 'transcript_source', 'transcript_biotype', 'havana_transcript', 'havana_transcript_version', 'tag', 'transcript_support_level', 'exon_number', 'exon_id', 'exon_version', 'ccds_id', 'protein_id', 'protein_version']

genes = gtf_df[gtf_df.transcript_biotype.isin(['protein_coding',
       'antisense', 'lincRNA',
       'TR_V_gene',
       'TR_V_pseudogene', 'TR_D_gene', 'TR_J_gene', 'TR_C_gene',
       'TR_J_pseudogene', 'IG_LV_gene', 'IG_V_gene', 'IG_V_pseudogene',
       'IG_J_gene', 'IG_C_gene', 'IG_C_pseudogene',
       'IG_D_gene', 'IG_D_pseudogene', 'IG_pseudogene'])].gene_id.unique()

len(genes)

31434

genes_df = gtf_df[gtf_df.transcript_biotype.isin(['protein_coding',
       'antisense', 'lincRNA',
        'TR_V_gene',
       'TR_V_pseudogene', 'TR_D_gene', 'TR_J_gene', 'TR_C_gene',
       'TR_J_pseudogene', 'IG_LV_gene', 'IG_V_gene', 'IG_V_pseudogene',
       'IG_J_gene', 'IG_C_gene', 'IG_C_pseudogene',
       'IG_D_gene', 'IG_D_pseudogene', 'IG_pseudogene'])].reset_index(drop = True)

genes_df

	seqname	source	feature	start	end	score	strand	frame	gene_id	gene_version	gene_name	gene_source	gene_biotype	havana_gene	havana_gene_version	transcript_id	transcript_version	transcript_name	transcript_source	transcript_biotype	havana_transcript	havana_transcript_version	tag	transcript_support_level	exon_number	exon_id	exon_version	ccds_id	protein_id	protein_version
0	1	ensembl_havana	transcript	3214482	3671498	NaN	-	0	ENSMUSG00000051951	5	Xkr4	ensembl_havana	protein_coding	OTTMUSG00000026353	2	ENSMUST00000070533	4	Xkr4-201	ensembl_havana	protein_coding	OTTMUST00000065166	1	CCDS,basic	1				CCDS14803
1	1	ensembl_havana	exon	3670552	3671498	NaN	-	0	ENSMUSG00000051951	5	Xkr4	ensembl_havana	protein_coding	OTTMUSG00000026353	2	ENSMUST00000070533	4	Xkr4-201	ensembl_havana	protein_coding	OTTMUST00000065166	1	CCDS,basic	1	1	ENSMUSE00000485541	3	CCDS14803
2	1	ensembl_havana	CDS	3670552	3671348	NaN	-	0	ENSMUSG00000051951	5	Xkr4	ensembl_havana	protein_coding	OTTMUSG00000026353	2	ENSMUST00000070533	4	Xkr4-201	ensembl_havana	protein_coding	OTTMUST00000065166	1	CCDS,basic	1	1			CCDS14803	ENSMUSP00000070648	4
3	1	ensembl_havana	start_codon	3671346	3671348	NaN	-	0	ENSMUSG00000051951	5	Xkr4	ensembl_havana	protein_coding	OTTMUSG00000026353	2	ENSMUST00000070533	4	Xkr4-201	ensembl_havana	protein_coding	OTTMUST00000065166	1	CCDS,basic	1	1			CCDS14803
4	1	ensembl_havana	exon	3421702	3421901	NaN	-	0	ENSMUSG00000051951	5	Xkr4	ensembl_havana	protein_coding	OTTMUSG00000026353	2	ENSMUST00000070533	4	Xkr4-201	ensembl_havana	protein_coding	OTTMUST00000065166	1	CCDS,basic	1	2	ENSMUSE00000449517	3	CCDS14803
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1387326	MT	insdc	stop_codon	13552	13554	NaN	-	0	ENSMUSG00000064368	1	mt-Nd6	insdc	protein_coding			ENSMUST00000082419	1	mt-Nd6-201	insdc	protein_coding			basic	NA	1
1387327	MT	insdc	transcript	14145	15288	NaN	+	0	ENSMUSG00000064370	1	mt-Cytb	insdc	protein_coding			ENSMUST00000082421	1	mt-Cytb-201	insdc	protein_coding			basic	NA
1387328	MT	insdc	exon	14145	15288	NaN	+	0	ENSMUSG00000064370	1	mt-Cytb	insdc	protein_coding			ENSMUST00000082421	1	mt-Cytb-201	insdc	protein_coding			basic	NA	1	ENSMUSE00000521548	1
1387329	MT	insdc	CDS	14145	15288	NaN	+	0	ENSMUSG00000064370	1	mt-Cytb	insdc	protein_coding			ENSMUST00000082421	1	mt-Cytb-201	insdc	protein_coding			basic	NA	1				ENSMUSP00000081003	1
1387330	MT	insdc	start_codon	14145	14147	NaN	+	0	ENSMUSG00000064370	1	mt-Cytb	insdc	protein_coding			ENSMUST00000082421	1	mt-Cytb-201	insdc	protein_coding			basic	NA	1

1387331 rows × 30 columns

#genes_df.to_csv("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_9Feb23/genes_df.csv")

#genes_df = pd.read_csv("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_9Feb23/genes_df.csv", index_col=0)

genes = genes_df.gene_id.unique()

len(genes_df.gene_id[genes_df.seqname.isin(['MT'])].unique())

13

%%R -o countdataSC
# Load the count data
countdataSC <- read.table("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/total/Total_counts_Pos_only.txt", header=TRUE, row.names=1)
#countdataSC <- read.table("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/total/Total_counts_PosandNeg.txt", header=TRUE, row.names=1)
dim(countdataSC)

[1] 55401   738

%%R
colnames(countdataSC) %>% head() %>% print()
dim(countdataSC)
colnames(countdataSC) <- gsub("\\.", "_", colnames(countdataSC))
dim(countdataSC)

[1] "E10.GFP.pos.F1.10" "E10.GFP.pos.F1.11" "E10.GFP.pos.F1.12"
[4] "E10.GFP.pos.F1.13" "E10.GFP.pos.F1.14" "E10.GFP.pos.F1.15"
[1] 55401   738

%%R
colnames(countdataSC) %>% head() %>% print()
#head(countdataSC)

[1] "E10_GFP_pos_F1_10" "E10_GFP_pos_F1_11" "E10_GFP_pos_F1_12"
[4] "E10_GFP_pos_F1_13" "E10_GFP_pos_F1_14" "E10_GFP_pos_F1_15"

%%R -o countdataSCMeta
countdataSCMeta <- read.table("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/BAM_LIST_18Jul23_Metadata.txt",
                             sep = '\t',
                             header = T)


rownames(countdataSCMeta) <- countdataSCMeta$sample
colnames(countdataSCMeta)[1] = "Cell"

%%R
countdataSCMeta %>% group_by(age, sex) %>% tally()

# A tibble: 14 × 3
# Groups:   age [7]
   age   sex        n
   <chr> <chr>  <int>
 1 E10.5 female    48
 2 E10.5 male      48
 3 E11.5 female    48
 4 E11.5 male      48
 5 E12.5 female    48
 6 E12.5 male      45
 7 E13.5 female    48
 8 E13.5 male      48
 9 E14.5 female    48
10 E14.5 male      48
11 E15.5 female    48
12 E15.5 male      72
13 E16.5 female    72
14 E16.5 male      72

%%R -o countdataSC -o obs_names -o var_names -i genes
# subset rownames
countdataSC <- countdataSC[rownames(countdataSC) %in% genes, ]
obs_names <- colnames(countdataSC)
var_names <- rownames(countdataSC)
countdataSC <- as.matrix(countdataSC)
print(dim(countdataSC[rownames(countdataSC) %in% genes, ]))

[1] 31434   738

Genome1 and 2 counts

%%R -o countdataSC_g1 -o countdataSC_g2
# Load the count data
#countdataSC_g1 <- read.table("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCount_OUT_18Jul21/E125_145_counts_genome1.txt", header=TRUE, row.names=1)
#countdataSC_g2 <- read.table("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCount_OUT_18Jul21/E125_145_counts_genome2.txt", header=TRUE, row.names=1)
countdataSC_g1 <- read.table("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/genome1/Total_counts_genome1_Pos_only.txt", header=TRUE, row.names=1)
countdataSC_g2 <- read.table("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/genome2/Total_counts_genome2_Pos_only.txt", header=TRUE, row.names=1)

%%R
colnames(countdataSC_g1) <- gsub("\\.", "_", colnames(countdataSC_g1))
colnames(countdataSC_g2) <- gsub("\\.", "_", colnames(countdataSC_g2))

dim(countdataSC_g1) %>% print()
dim(countdataSC_g2) %>% print()

[1] 55401   738
[1] 55401   738

%%R -o countdataSC_g1 -o obs_names_g1 -o var_names_g1 -i genes
# subset rownames
countdataSC_g1 <- countdataSC_g1[rownames(countdataSC_g1) %in% genes, ]
obs_names_g1 <- colnames(countdataSC_g1)
var_names_g1 <- rownames(countdataSC_g1)
countdataSC_g1 <- as.matrix(countdataSC_g1)
print(dim(countdataSC_g1[rownames(countdataSC_g1) %in% genes, ]))

[1] 31434   738

%%R 
#head(countdataSC_g1) 
colnames(countdataSC_g1) %in% rownames(countdataSCMeta) %>% table()
#colnames(countdataSC_g1)

.
TRUE 
 738 

%%R -o countdataSC_g2 -o obs_names_g2 -o var_names_g2 -i genes
# subset rownames
countdataSC_g2 <- countdataSC_g2[rownames(countdataSC_g2) %in% genes, ]
obs_names_g2 <- colnames(countdataSC_g2)
var_names_g2 <- rownames(countdataSC_g2)
countdataSC_g2 <- as.matrix(countdataSC_g2)
print(dim(countdataSC_g2[rownames(countdataSC_g2) %in% genes, ]))

[1] 31434   738

%%R
is.na(countdataSC_g1) %>% table()
is.na(countdataSC_g2) %>% table()

.
   FALSE 
23198292 

SCANPY

gcAnndata = sc.AnnData(X = countdataSC.T, obs = obs_names, var = var_names)

# Read in saved gcAnndata
#gcAnndata=sc.read_h5ad("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/gcAnndata_17Jul23.h5ad")
#gcAnndata

gcAnndata.obs.rename(columns={0:'Sample'}, inplace=True)
gcAnndata.var.rename(columns={0:'geneid'}, inplace=True)

gcAnndata.var.index = gcAnndata.var.geneid.to_list()
gcAnndata.obs.index = gcAnndata.obs.Sample.to_list()

annot = sc.queries.biomart_annotations(
    "mmusculus",
    ["ensembl_gene_id", "start_position", "end_position", "chromosome_name", "external_gene_name"],
    host="nov2020.archive.ensembl.org",
    use_cache='TRUE',
    ).set_index("ensembl_gene_id")

gcAnndata.var[annot.columns] = annot

gcAnndata.var.index = gcAnndata.var.geneid.tolist()

gcAnndata

AnnData object with n_obs × n_vars = 738 × 31434
    obs: 'Sample'
    var: 'geneid', 'start_position', 'end_position', 'chromosome_name', 'external_gene_name'

gcAnndata.var_names_make_unique()

gcAnndata.n_obs

738

gcAnndata.var.chromosome_name=='MT'

ENSMUSG00000051951    False
ENSMUSG00000089699    False
ENSMUSG00000102343    False
ENSMUSG00000025900    False
ENSMUSG00000025902    False
                      ...  
ENSMUSG00000065947     True
ENSMUSG00000064363     True
ENSMUSG00000064367     True
ENSMUSG00000064368     True
ENSMUSG00000064370     True
Name: chromosome_name, Length: 31434, dtype: bool

gcAnndata.var['mt'] = gcAnndata.var.chromosome_name=='MT' # annotate the group of mitochondrial genes as 'mt'
gcAnndata.var['mt']

ENSMUSG00000051951    False
ENSMUSG00000089699    False
ENSMUSG00000102343    False
ENSMUSG00000025900    False
ENSMUSG00000025902    False
                      ...  
ENSMUSG00000065947     True
ENSMUSG00000064363     True
ENSMUSG00000064367     True
ENSMUSG00000064368     True
ENSMUSG00000064370     True
Name: mt, Length: 31434, dtype: bool

sc.pp.calculate_qc_metrics(gcAnndata, qc_vars=['mt'], percent_top=None, log1p=False, inplace=True)

gcAnndata.obs['sex'] = countdataSCMeta['sex']

gcAnndata.obs['stage'] = countdataSCMeta['age']

gcAnndata.obs['Embryo'] = countdataSCMeta['embryo']

gcAnndata.obs['stage_sex'] = gcAnndata.obs.sex.astype('str') + "_" + gcAnndata.obs.stage.astype('str')

gcAnndata.obs

	Sample	n_genes_by_counts	total_counts	total_counts_mt	pct_counts_mt	sex	stage	Embryo	stage_sex
E10_GFP_pos_F1_10	E10_GFP_pos_F1_10	8707	715292	918	0.128339	female	E10.5	F1	female_E10.5
E10_GFP_pos_F1_11	E10_GFP_pos_F1_11	8473	1564689	5792	0.370169	female	E10.5	F1	female_E10.5
E10_GFP_pos_F1_12	E10_GFP_pos_F1_12	8206	2310070	3992	0.172809	female	E10.5	F1	female_E10.5
E10_GFP_pos_F1_13	E10_GFP_pos_F1_13	10345	1608779	6207	0.385821	female	E10.5	F1	female_E10.5
E10_GFP_pos_F1_14	E10_GFP_pos_F1_14	8338	1320374	5065	0.383603	female	E10.5	F1	female_E10.5
...	...	...	...	...	...	...	...	...	...
M4_GFPP_P2_B6	M4_GFPP_P2_B6	5273	78485	949	1.209148	male	E12.5	M4	male_E12.5
M4_GFPP_P2_B7	M4_GFPP_P2_B7	6595	2647587	22935	0.866260	male	E12.5	M4	male_E12.5
M4_GFPP_P2_B8	M4_GFPP_P2_B8	5555	1920124	20754	1.080868	male	E12.5	M4	male_E12.5
M4_GFPP_P2_B9	M4_GFPP_P2_B9	5391	1287828	9147	0.710266	male	E12.5	M4	male_E12.5
M4_GFPP_P2_D2	M4_GFPP_P2_D2	6042	3026218	22180	0.732928	male	E12.5	M4	male_E12.5

738 rows × 9 columns

gcAnndata

AnnData object with n_obs × n_vars = 738 × 31434
    obs: 'Sample', 'n_genes_by_counts', 'total_counts', 'total_counts_mt', 'pct_counts_mt', 'sex', 'stage', 'Embryo', 'stage_sex'
    var: 'geneid', 'start_position', 'end_position', 'chromosome_name', 'external_gene_name', 'mt', 'n_cells_by_counts', 'mean_counts', 'pct_dropout_by_counts', 'total_counts'

gcAnndata.obs['stage_sex'].value_counts()

female_E16.5    72
male_E16.5      71
male_E15.5      70
female_E10.5    48
male_E10.5      48
male_E11.5      48
female_E11.5    48
female_E12.5    48
female_E13.5    48
male_E13.5      48
male_E14.5      48
female_E14.5    48
female_E15.5    48
male_E12.5      45
Name: stage_sex, dtype: int64

gcAnndata.obs['sex'].head()

E10_GFP_pos_F1_10    female
E10_GFP_pos_F1_11    female
E10_GFP_pos_F1_12    female
E10_GFP_pos_F1_13    female
E10_GFP_pos_F1_14    female
Name: sex, dtype: object

gcAnndata.obs['CellID'] = gcAnndata.obs.index.tolist()

gcAnndata.var['Gene'] = gcAnndata.var.index.tolist()

sc.pl.violin(gcAnndata, ['n_genes_by_counts', 'total_counts', 'pct_counts_mt'],
             jitter=0.4, multi_panel=True)

... storing 'sex' as categorical
... storing 'stage' as categorical
... storing 'Embryo' as categorical
... storing 'stage_sex' as categorical
... storing 'chromosome_name' as categorical
... storing 'external_gene_name' as categorical

sc.pp.filter_cells(gcAnndata, min_genes = 3500)
sc.pp.filter_cells(gcAnndata, max_genes = 10000)
sc.pp.filter_cells(gcAnndata, min_counts = 500000)
sc.pp.filter_genes(gcAnndata, min_cells = 5)
gcAnndata = gcAnndata[gcAnndata.obs['pct_counts_mt'] < 5, :]

filtered out 40 cells that have less than 3500 genes expressed
filtered out 6 cells that have more than 10000 genes expressed
filtered out 7 cells that have less than 500000 counts
filtered out 10260 genes that are detected in less than 5 cells

#gcAnndata.obs.to_csv("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/gcAnndata_obs.csv")

# Retain same cells for allele-specific analyses
#keep = gcAnndata.obs.Sample
#keep.to_csv(".../keep.csv")

gcAnndata.layers["counts"] = gcAnndata[gcAnndata.obs_names, gcAnndata.var_names].X.copy()

gcAnndata

AnnData object with n_obs × n_vars = 681 × 21174
    obs: 'Sample', 'n_genes_by_counts', 'total_counts', 'total_counts_mt', 'pct_counts_mt', 'sex', 'stage', 'Embryo', 'stage_sex', 'CellID', 'n_genes', 'n_counts'
    var: 'geneid', 'start_position', 'end_position', 'chromosome_name', 'external_gene_name', 'mt', 'n_cells_by_counts', 'mean_counts', 'pct_dropout_by_counts', 'total_counts', 'Gene', 'n_cells'
    layers: 'counts'

sc.pl.violin(gcAnndata, ['n_genes_by_counts', 'total_counts', 'pct_counts_mt'],
             jitter=0.4, multi_panel=True)

plt.rcParams['figure.figsize'] = [3, 2.5]
svm = sns.violinplot(data=gcAnndata.obs, y="stage", x="pct_counts_mt", hue="sex", split=True, inner="quart", linewidth=1);
sns.despine(left=True)
figure = svm.get_figure()    
#figure.savefig(".../mito_counts2.png", dpi=300)

plt.rcParams['figure.figsize'] = [11.5, 2.5]
svm = sns.swarmplot(data=gcAnndata.obs, x="stage", y="pct_counts_mt", hue="sex", dodge=True, s = 3, legend=True);
figure = svm.get_figure()    
#figure.savefig(".../mito_counts.png", dpi=300)

plt.rcParams['figure.figsize'] = [11.5, 2.5]
svm = sns.swarmplot(data=gcAnndata.obs, x="stage", y="n_genes_by_counts", hue="sex", s = 3, dodge=True);
figure = svm.get_figure()    
#figure.savefig(".../n_genes_by_counts.png", dpi=300)

plt.rcParams['figure.figsize'] = [11.5, 2.5]
svm = sns.swarmplot(data=gcAnndata.obs, x = "stage", y = "total_counts", hue = "sex", s = 3, dodge = True);
figure = svm.get_figure()    
#figure.savefig(".../total_counts.png", dpi=300)

plt.rcParams['figure.figsize'] = [5, 5]

gcAnndata.raw = gcAnndata

sc.pp.normalize_total(gcAnndata, exclude_highly_expressed = True, max_fraction = 0.10, target_sum=1e4)

normalizing counts per cell The following highly-expressed genes are not considered during normalization factor computation:
[]
    finished (0:00:00)

sc.pp.log1p(gcAnndata)

sc.pp.highly_variable_genes(gcAnndata, flavor='seurat_v3', n_top_genes=800)

If you pass `n_top_genes`, all cutoffs are ignored.
extracting highly variable genes
--> added
    'highly_variable', boolean vector (adata.var)
    'highly_variable_rank', float vector (adata.var)
    'means', float vector (adata.var)
    'variances', float vector (adata.var)
    'variances_norm', float vector (adata.var)

gcAnndata.var['highly_variable'].value_counts()

False    20374
True       800
Name: highly_variable, dtype: int64

sc.pl.highly_variable_genes(gcAnndata)

sc.tl.pca(gcAnndata, svd_solver='arpack')

computing PCA
    on highly variable genes
    with n_comps=50
    finished (0:00:00)

sc.pl.pca(gcAnndata, color=['stage_sex'], size=200, ec="black", linewidth=0.5, frameon=True)#

sc.pp.neighbors(gcAnndata, n_neighbors=5, n_pcs=50)

computing neighbors
    using 'X_pca' with n_pcs = 50
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:02)

sc.tl.leiden(gcAnndata, resolution = 0.7, random_state = 55063) # Perform clustering

running Leiden clustering
    finished: found 15 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:00)

sc.tl.umap(gcAnndata, random_state = 55063)

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:01)

sc.pl.umap(gcAnndata, color=['stage_sex'], size=100, ec="black", linewidth=0.5, frameon=True)

sc.pl.umap(gcAnndata, color=['stage_sex'], size=100, ec="black", linewidth=0.5, frameon=True)

sc.tl.tsne(gcAnndata, n_pcs=50, perplexity=40, random_state = 55063)

computing tSNE
    using 'X_pca' with n_pcs = 50
    using sklearn.manifold.TSNE
    finished: added
    'X_tsne', tSNE coordinates (adata.obsm) (0:00:02)

#plt.rcParams['figure.figsize'] = [5,5]
sc.pl.tsne(gcAnndata, color=['stage_sex'], size=150, ec="black", linewidth=0.5, frameon=True)#, save = '_stage_sex.png')

sc.pl.tsne(gcAnndata, color=["leiden", 'stage_sex', 'Embryo'],legend_loc="on data", size=150, edgecolor="black", linewidths=0.5, frameon=True, legend_fontsize=8, legend_fontoutline=1)

sc.pl.tsne(gcAnndata, color=['sex', 'stage', 'stage_sex'], size=150, ec="black", linewidth=0.5, frameon=True, show=False)#, save="_multi.png")

[<AxesSubplot: title={'center': 'sex'}, xlabel='tSNE1', ylabel='tSNE2'>,
 <AxesSubplot: title={'center': 'stage'}, xlabel='tSNE1', ylabel='tSNE2'>,
 <AxesSubplot: title={'center': 'stage_sex'}, xlabel='tSNE1', ylabel='tSNE2'>]

# colour scheme for nice plots
colours = ["#f1eef6", "#d4b9da", "#c994c7", "#df65b0", "#e7298a", "#ce1256", "#91003f", 
           "#eff3ff", "#c6dbef", "#9ecae1", "#6baed6", "#4292c6", "#2171b5", "#084594"]


cats = ["male_E10.5", "male_E11.5", "male_E12.5", "male_E13.5", "male_E14.5", "male_E15.5", "male_E16.5",
       "female_E10.5", "female_E11.5", "female_E12.5", "female_E13.5", "female_E14.5", "female_E15.5", "female_E16.5"]

sc.pl.tsne(gcAnndata, color = ['stage_sex'], palette = colours, size = 150, ec = "black", linewidth = 0.5, frameon = True, save = '_stage_sex.pdf')

WARNING: saving figure to file /users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Figures/tsne_stage_sex.pdf

gcAnndata.obs.Sample = gcAnndata.obs.Sample.astype('category')

sc.pl.pca(gcAnndata, color='stage_sex', size=300, ec="black", frameon=True, legend_loc="on data", legend_fontsize=4, linewidth=0.2)

sc.pl.pca(gcAnndata, color='stage_sex', size=800, ec="black", frameon=True, legend_fontsize=4, linewidth=0.2, projection='3d')

sc.pl.correlation_matrix(gcAnndata, groupby="Sample", figsize=[5,4])

sc.pl.correlation_matrix(gcAnndata, groupby="stage_sex", 
                         figsize=[5,4])#,
                         #save="_stage_sex.pdf")

WARNING: dendrogram data not found (using key=dendrogram_stage_sex). Running `sc.tl.dendrogram` with default parameters. For fine tuning it is recommended to run `sc.tl.dendrogram` independently.
    using 'X_pca' with n_pcs = 50
Storing dendrogram info using `.uns['dendrogram_stage_sex']`

gcAnndata_f = gcAnndata[gcAnndata.obs.sex == 'female']

gcAnndata[:,gcAnndata.var[gcAnndata.var.chromosome_name == 'X'].geneid]

View of AnnData object with n_obs × n_vars = 681 × 734
    obs: 'Sample', 'n_genes_by_counts', 'total_counts', 'total_counts_mt', 'pct_counts_mt', 'sex', 'stage', 'Embryo', 'stage_sex', 'CellID', 'n_genes', 'n_counts', 'leiden'
    var: 'geneid', 'start_position', 'end_position', 'chromosome_name', 'external_gene_name', 'mt', 'n_cells_by_counts', 'mean_counts', 'pct_dropout_by_counts', 'total_counts', 'Gene', 'n_cells', 'highly_variable', 'highly_variable_rank', 'means', 'variances', 'variances_norm'
    uns: 'log1p', 'hvg', 'pca', 'stage_sex_colors', 'neighbors', 'leiden', 'umap', 'tsne', 'leiden_colors', 'Embryo_colors', 'sex_colors', 'stage_colors', 'dendrogram_Sample', 'dendrogram_stage_sex'
    obsm: 'X_pca', 'X_umap', 'X_tsne'
    varm: 'PCs'
    layers: 'counts'
    obsp: 'distances', 'connectivities'

Xgenes = gcAnndata.var.index[gcAnndata.var.chromosome_name=="X"].to_list()
C9genes = gcAnndata.var.index[gcAnndata.var.chromosome_name=="9"].to_list()
Agenes = gcAnndata.var.index[~gcAnndata.var.chromosome_name.isin(['X', 'Y', 'mt'])].to_list()

len(Xgenes)

734

gcAnndata.obs["Chr X"] = (np.mean(gcAnndata[:, Xgenes].X, axis=1) / np.mean(gcAnndata[:, Agenes].X, axis=1)).tolist()

gcAnndata.obs["Chr 9"] = (np.mean(gcAnndata[:, C9genes].X, axis=1) / np.mean(gcAnndata[:, Agenes].X, axis=1)).tolist()

germXA_data = gcAnndata.obs["stage_sex"].to_frame().join(gcAnndata.obs["Chr 9"]).join(gcAnndata.obs["Chr X"])
#Melt the data to long format
germXA_data_melted = germXA_data.melt(id_vars="stage_sex", var_name="key", value_name="value")

germXA_data_melted.groupby(['stage_sex', 'key']).describe()

		value
		count	mean	std	min	25%	50%	75%	max
stage_sex	key
female_E10.5	Chr 9	47.0	1.012043	0.026427	0.958342	0.989431	1.009407	1.033937	1.077519
	Chr X	47.0	0.822947	0.070499	0.640044	0.782758	0.825400	0.877600	0.962569
female_E11.5	Chr 9	47.0	1.029672	0.026420	0.975295	1.012752	1.025092	1.044855	1.101905
	Chr X	47.0	0.847130	0.064805	0.654526	0.801558	0.862572	0.890400	0.973839
female_E12.5	Chr 9	48.0	0.998605	0.045742	0.895704	0.973150	1.000592	1.015991	1.169789
	Chr X	48.0	0.889870	0.092939	0.673507	0.827104	0.886237	0.959413	1.105513
female_E13.5	Chr 9	40.0	1.044379	0.044534	0.930172	1.018523	1.053287	1.073795	1.122464
	Chr X	40.0	0.992893	0.121615	0.733157	0.909683	0.978785	1.080452	1.396950
female_E14.5	Chr 9	48.0	1.051697	0.051178	0.940974	1.015260	1.054081	1.075947	1.180031
	Chr X	48.0	1.063192	0.122279	0.873746	0.970958	1.052641	1.141462	1.377386
female_E15.5	Chr 9	47.0	1.037858	0.040084	0.943308	1.011347	1.041363	1.061268	1.135436
	Chr X	47.0	1.035229	0.102241	0.812545	0.973312	1.026228	1.083537	1.352903
female_E16.5	Chr 9	71.0	1.039123	0.045916	0.907251	1.017328	1.042530	1.061850	1.247615
	Chr X	71.0	1.040803	0.110789	0.752412	0.969280	1.046088	1.123013	1.257005
male_E10.5	Chr 9	24.0	1.038062	0.061847	0.970524	1.001445	1.020613	1.040375	1.216107
	Chr X	24.0	0.773014	0.080408	0.593542	0.736125	0.773389	0.827852	0.906810
male_E11.5	Chr 9	44.0	1.015869	0.033405	0.893333	1.000197	1.016201	1.034641	1.102942
	Chr X	44.0	0.761341	0.052476	0.663016	0.730005	0.750823	0.802822	0.925153
male_E12.5	Chr 9	40.0	1.001168	0.035163	0.934700	0.982239	1.001831	1.024509	1.082474
	Chr X	40.0	0.691051	0.046065	0.590866	0.665667	0.687883	0.720373	0.819208
male_E13.5	Chr 9	45.0	0.998012	0.041980	0.886521	0.974844	0.999950	1.028868	1.079159
	Chr X	45.0	0.712141	0.078149	0.522520	0.679215	0.709172	0.767981	0.848880
male_E14.5	Chr 9	48.0	1.023912	0.027087	0.977528	1.002257	1.020333	1.043324	1.084641
	Chr X	48.0	0.784864	0.059649	0.652369	0.745806	0.791983	0.821869	0.938275
male_E15.5	Chr 9	65.0	1.004693	0.031430	0.935337	0.982872	1.003668	1.026745	1.085654
	Chr X	65.0	0.778226	0.068872	0.613075	0.740555	0.768841	0.811646	1.118926
male_E16.5	Chr 9	67.0	1.035236	0.037549	0.956945	1.009372	1.034423	1.055281	1.190011
	Chr X	67.0	0.660736	0.048407	0.526992	0.631664	0.659311	0.690349	0.774454

plt.rcParams["figure.figsize"]=4,4
bx = sns.violinplot(x="stage_sex", y="value",
            hue="key", palette=["#0D8DB3","#C70039"],fliersize=0.1,linewidth=0.5,split=True,scale="count",inner="quartile",
            data=germXA_data_melted)
bx.set(xlabel="")
bx.set_ylabel("Chromosome:Autosome ratio", fontsize=8)
bx.set_xticklabels(bx.get_xticklabels(), rotation=40, fontsize=8,horizontalalignment="right", rotation_mode="anchor", visible=True)
bx.grid(linestyle='-', linewidth='0.1')
bx.tick_params(
    axis="both",          # changes apply to the x-axis
    which="major",      # both major and minor ticks are affected
    bottom=True,      # ticks along the bottom edge are off
    top=False,  left=True, labeltop=False,      # ticks along the top edge are off
    labelbottom=True, pad=0.5, length=1.5)
bx.axhline(y=0.5,color='gray',linestyle='--')
bx.axhline(y=1,color='gray',linestyle='--')
plt.legend(loc="upper right", fontsize=6, frameon=False)
plt.tight_layout()

#figure = svm.get_figure()    
#plt.savefig('.../X_Aratios.pdf', dpi=600)

Stats

from scipy import stats

stats.mannwhitneyu(germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('male') & germXA_data_melted['key'].isin(['Chr X'])].value,
              germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('female') & germXA_data_melted['key'].isin(['Chr X'])].value)

MannwhitneyuResult(statistic=67915.0, pvalue=3.4661425085809535e-29)

stats.mannwhitneyu(germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('male') & germXA_data_melted['key'].isin(['Chr 9'])].value,
              germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('female') & germXA_data_melted['key'].isin(['Chr 9'])].value)

MannwhitneyuResult(statistic=106278.0, pvalue=0.006759871068865442)

# plt.rcParams["figure.figsize"]=10,3
#p = sns.scatterplot(gcAnndata.obs.Sample, gcAnndata.obs['Chr X'], hue=gcAnndata.obs.sex, legend=False)
# plt.setp(p.get_xticklabels(), rotation=45, ha="right", rotation_mode="anchor");

stats.mannwhitneyu(germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('female_E14.5') & germXA_data_melted['key'].isin(['Chr X'])].value,
              germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('male_E14.5') & germXA_data_melted['key'].isin(['Chr X'])].value)
# At E14.5, female X output is significantly different to E14.5 male

MannwhitneyuResult(statistic=3446.0, pvalue=1.3128901010109332e-06)

stats.mannwhitneyu(germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('female_E14.5') & germXA_data_melted['key'].isin(['Chr 9'])].value,
              germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('male_E14.5') & germXA_data_melted['key'].isin(['Chr 9'])].value)
# At E14.5, female 9 output is NOT significantly different to E14.5 male

MannwhitneyuResult(statistic=2741.0, pvalue=0.06432346407530999)

stats.mannwhitneyu(germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('female_E14.5') & germXA_data_melted['key'].isin(['Chr X'])].value,
              germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('female_E14.5') & germXA_data_melted['key'].isin(['Chr 9'])].value)
# At E14.5, female X output is NOT significantly different to E14.5 female 9 output

MannwhitneyuResult(statistic=1131.0, pvalue=0.8805938792307255)

stats.mannwhitneyu(germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('male_E14.5') & germXA_data_melted['key'].isin(['Chr X'])].value,
              germXA_data_melted[germXA_data_melted['stage_sex'].str.contains('male_E14.5') & germXA_data_melted['key'].isin(['Chr 9'])].value)
# At E14.5, male X output is significantly different to E14.5 male 9 output

MannwhitneyuResult(statistic=2465.0, pvalue=2.6222181827301973e-08)

PAGA

sc.tl.paga(gcAnndata, groups="stage_sex")
#sc.tl.paga(gcAnndata, groups="stage_sex_celltype")

running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:00)

sc.pl.paga(gcAnndata,
           threshold = 0.1561, 
           fontsize=10,
           fontoutline=1, 
           layout='fa',
           save='_PAGA.pdf')

WARNING: Package 'fa2' is not installed, falling back to layout 'fr'.To use the faster and better ForceAtlas2 layout, install package 'fa2' (`pip install fa2`).
--> added 'pos', the PAGA positions (adata.uns['paga'])
WARNING: saving figure to file /users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Figures/paga_PAGA.pdf

gcAnndata.uns['iroot'] = np.flatnonzero(gcAnndata.obs["stage_sex"]  == "male_E10.5")[0]

sc.tl.dpt(gcAnndata, 
          n_dcs = 15, 
          n_branchings = 2)

computing Diffusion Pseudotime using n_dcs=15
    this uses a hierarchical implementation
WARNING: shifting branching point away from maximal kendall-tau correlation (suppress this with `allow_kendall_tau_shift=False`)
    finished: added
    'dpt_pseudotime', the pseudotime (adata.obs)
    'dpt_groups', the branching subgroups of dpt (adata.obs)
    'dpt_order', cell order (adata.obs) (0:00:00)

sc.pl.tsne(gcAnndata, color=["dpt_pseudotime", "stage_sex"], size=200,frameon=True, ec="black", linewidth=0.4)
sc.pl.tsne(gcAnndata, color=["dpt_pseudotime"], size=200,frameon=True, ec="black", linewidth=0.4)#, save = '_pseudotime.pdf')

DE gene and marker analysis

sc.pl.matrixplot(gcAnndata, var_names=["Eif2s3y", "Ddx3y", "Uty", "Usp9y", "Uba1y", "Kdm5d", "Sly", "Zfy2"], 
                 gene_symbols="external_gene_name",
                 cmap=heatcolors_wr, 
                 groupby="stage_sex", 
                 #dendrogram = True,
                 swap_axes = True,
                 standard_scale="var"),
                 #save = '.../_Ygenes.png')

(None,)

#gcAnndata.var
sc.pl.tsne(gcAnndata, 
           color=["Tfap2c", "Prdm14", "Pou5f1", "Nanog", "Dnmt3a", "Dnmt3l", "Dnmt3b", "Dnmt3c", "Tet1", "Tet2", "Lefty1", "Lefty2", "Etv1",
                  "Pitx2", "Hesx1", "Egr4", "Phlda2", "Gata2", "Rec8", "Stra8", "Prdm9", "Spo11", "Atr", "Atm"], 
           gene_symbols = 'external_gene_name', 
           use_raw=True, 
           legend_fontsize=6, 
           size=60, 
           edgecolor="black", 
           linewidths=0.1,
           wspace=0.05, 
           hspace=0.2, 
           cmap=heatcolors, 
           ncols=7)#,
           #save="_male_female_candidategenes")

#gcAnndata.var
sc.pl.tracksplot(gcAnndata, var_names=["Tfap2c", "Prdm14", "Pou5f1", "Nanog", 
                                       "Dnmt3a", "Dnmt3l", "Dnmt3b", "Dnmt3c", "Tet1", "Tet2", 
                                       "Lefty1", "Lefty2", "Etv1", "Pitx2", "Hesx1", "Egr4", 
                                       "Phlda2", "Gata2", "Rec8", "Stra8", "Prdm9", "Spo11", 
                                       "Atr", "Atm", "Msh6", "Aurka"], 
                 gene_symbols = 'external_gene_name', 
                 use_raw=False, 
                 dendrogram=False,
                 groupby='stage_sex',
                 #save = "tracksplot_malefemale.pdf",
                 )

%%R -o Ezh2_derep_X
Ezh2_derep_X <- read.delim("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Table_fem_chrx.txt")
Ezh2_derep_All <- read.delim("~/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Table_fem.txt")

sc.pl.matrixplot(gcAnndata_f, 
                 var_names = gcAnndata_f.var[gcAnndata_f.var.geneid.isin(Ezh2_derep_X.ensembl_gene_id)].external_gene_name,
                 gene_symbols="external_gene_name",
                 cmap=heatcolors_wr, 
                 groupby="stage_sex", 
                 #dendrogram = True,
                 swap_axes = True,
                 standard_scale="var",
                 figsize = [3,8], save="_Ezh2_derep_X.pdf")

WARNING: saving figure to file /users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Figures/matrixplot__Ezh2_derep_X.pdf

sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", 
                        groups=["female_E16.5", "female_E15.5", "female_E14.5", "female_E13.5", "female_E12.5", "female_E11.5", "female_E10.5"], 
                        reference = 'rest', 
                        method='wilcoxon', 
                        tie_correct=True, 
                        key_added="female", 
                        pts=True)

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:08)

sc.tl.rank_genes_groups(gcAnndata, 
                        groupby="stage_sex", 
                        groups=["male_E16.5", "male_E15.5", "male_E14.5", "male_E13.5", "male_E12.5", "male_E11.5", "male_E10.5"], 
                        reference = 'rest', 
                        method='wilcoxon', 
                        tie_correct=True, 
                        key_added="male", 
                        pts=True)

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:06)

## Male E16.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["male_E16.5"], reference = "male_E15.5", method='wilcoxon', tie_correct=True, key_added="male", pts=True)
m_df_E16_5 = sc.get.rank_genes_groups_df(gcAnndata, group="male_E16.5", key="male", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
m_df_E16_5[1:20]
## Male E15.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["male_E15.5"], reference = "male_E14.5", method='wilcoxon', tie_correct=True, key_added="male", pts=True)
m_df_E15_5 = sc.get.rank_genes_groups_df(gcAnndata, group="male_E15.5", key="male", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
m_df_E15_5[1:20]
## Male E14.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["male_E14.5"], reference = "male_E13.5", method='wilcoxon', tie_correct=True, key_added="male", pts=True)
m_df_E14_5 = sc.get.rank_genes_groups_df(gcAnndata, group="male_E14.5", key="male", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
m_df_E14_5[1:20]
## Male E13.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["male_E13.5"], reference = "male_E12.5", method='wilcoxon', tie_correct=True, key_added="male", pts=True)
m_df_E13_5 = sc.get.rank_genes_groups_df(gcAnndata, group="male_E13.5", key="male", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
m_df_E13_5[1:20]
## Male E12.5 
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["male_E12.5"], reference = "male_E11.5", method='wilcoxon', tie_correct=True, key_added="male", pts=True)
m_df_E12_5 = sc.get.rank_genes_groups_df(gcAnndata, group="male_E12.5", key="male", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
m_df_E12_5[1:20]
## Male E11.5 
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["male_E11.5"], reference = "male_E10.5", method='wilcoxon', tie_correct=True, key_added="male", pts=True)
m_df_E11_5 = sc.get.rank_genes_groups_df(gcAnndata, group="male_E11.5", key="male", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
m_df_E11_5[1:20]

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
--> Few observations in a group for normal approximation (<=25). Lower test accuracy.
    finished: added to `.uns['male']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)

	names	scores	logfoldchanges	pvals	pvals_adj	external_gene_name	pct_nz_group
1	ENSMUSG00000056234	6.565826	213.050735	5.174525e-11	2.406918e-07	Ncoa4	1.000000
2	ENSMUSG00000039678	6.559144	553.579590	5.411766e-11	2.406918e-07	Tbc1d13	1.000000
3	ENSMUSG00000017119	6.552553	358.968750	5.656180e-11	2.406918e-07	Nbr1	1.000000
4	ENSMUSG00000004056	6.527918	203.101013	6.669024e-11	2.406918e-07	Akt2	1.000000
5	ENSMUSG00000031976	6.522604	383.036194	6.909717e-11	2.406918e-07	Urb2	0.977273
6	ENSMUSG00000002996	6.501409	232.760284	7.957129e-11	2.406918e-07	Hbp1	1.000000
7	ENSMUSG00000020211	6.459280	220.519241	1.052023e-10	2.784441e-07	Sf3a2	0.977273
8	ENSMUSG00000005672	6.404060	inf	1.512987e-10	3.559553e-07	Kit	1.000000
9	ENSMUSG00000030091	6.378636	359.181885	1.786723e-10	3.783207e-07	Nup210	1.000000
10	ENSMUSG00000025324	6.329055	187.015335	2.466673e-10	4.396694e-07	Atp10a	1.000000
11	ENSMUSG00000032479	6.327239	748.310608	2.495876e-10	4.396694e-07	Map4	1.000000
12	ENSMUSG00000030082	6.314525	776.716431	2.709929e-10	4.396694e-07	Sec61a1	1.000000
13	ENSMUSG00000052488	6.301390	447.765533	2.949888e-10	4.396694e-07	Cherp	1.000000
14	ENSMUSG00000036057	6.292960	283.085724	3.114688e-10	4.396694e-07	Ptpn23	0.977273
15	ENSMUSG00000033257	6.274337	327.267731	3.511266e-10	4.646722e-07	Ttll4	1.000000
16	ENSMUSG00000020536	6.260870	350.192352	3.828347e-10	4.768319e-07	Llgl1	1.000000
17	ENSMUSG00000028454	6.222013	172.675293	4.908154e-10	5.612534e-07	Pigo	1.000000
18	ENSMUSG00000032637	6.217970	480.843689	5.036278e-10	5.612534e-07	Atxn2l	1.000000
19	ENSMUSG00000025153	6.179469	inf	6.431770e-10	6.648344e-07	Fasn	1.000000

## Female E16.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E16.5"], reference = "female_E15.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
f_df_E16_5 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E16.5", key="female", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
f_df_E16_5[1:20]
## Female E15.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E15.5"], reference = "female_E14.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
f_df_E15_5 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E15.5", key="female", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
f_df_E15_5[1:20]
## Female E14.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E14.5"], reference = "female_E13.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
f_df_E14_5 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E14.5", key="female", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
f_df_E14_5[1:20]
## Female E13.5
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E13.5"], reference = "female_E12.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
f_df_E13_5 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E13.5", key="female", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
f_df_E13_5[1:20]
## Female E12.5 
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E12.5"], reference = "female_E11.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
f_df_E12_5 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E12.5", key="female", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
f_df_E12_5[1:20]
## Male E11.5 
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E11.5"], reference = "female_E10.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
f_df_E11_5 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E11.5", key="female", pval_cutoff=0.01, log2fc_min = 1.5, gene_symbols="external_gene_name")
f_df_E11_5[1:20]

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)
ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)

	names	scores	logfoldchanges	pvals	pvals_adj	external_gene_name	pct_nz_group
1	ENSMUSG00000005672	7.853261	inf	4.053579e-15	4.291524e-11	Kit	1.000000
2	ENSMUSG00000035632	7.566010	296.673340	3.848639e-14	2.716370e-10	Cnot3	1.000000
3	ENSMUSG00000024949	7.512884	631.347900	5.783882e-14	3.061698e-10	Sf1	1.000000
4	ENSMUSG00000036097	7.430614	229.695465	1.080946e-13	4.144266e-10	Slf2	1.000000
5	ENSMUSG00000016933	7.419645	474.032745	1.174346e-13	4.144266e-10	Plcg1	1.000000
6	ENSMUSG00000003435	7.380548	446.897797	1.576390e-13	4.525582e-10	Supt5	1.000000
7	ENSMUSG00000026024	7.365295	280.987885	1.767555e-13	4.525582e-10	Als2	1.000000
8	ENSMUSG00000030662	7.354002	inf	1.923597e-13	4.525582e-10	Ipo5	1.000000
9	ENSMUSG00000028430	7.286180	529.008667	3.188652e-13	6.143860e-10	Nol6	1.000000
10	ENSMUSG00000030082	7.286049	694.304688	3.191767e-13	6.143860e-10	Sec61a1	1.000000
11	ENSMUSG00000022443	7.233193	470.779022	4.717680e-13	8.324346e-10	Myh9	1.000000
12	ENSMUSG00000024740	7.202788	inf	5.899351e-13	9.608681e-10	Ddb1	1.000000
13	ENSMUSG00000004207	7.172540	615.570374	7.361867e-13	1.098000e-09	Psap	1.000000
14	ENSMUSG00000021938	7.165004	457.088776	7.778410e-13	1.098000e-09	Pspc1	1.000000
15	ENSMUSG00000066232	7.104842	271.195984	1.204604e-12	1.549117e-09	Ipo7	1.000000
16	ENSMUSG00000015697	7.095524	301.461884	1.288625e-12	1.549117e-09	Setdb1	1.000000
17	ENSMUSG00000031386	7.085577	inf	1.384655e-12	1.549117e-09	Hcfc1	1.000000
18	ENSMUSG00000025261	7.078118	inf	1.461254e-12	1.549117e-09	Huwe1	1.000000
19	ENSMUSG00000006932	7.068639	401.898010	1.564605e-12	1.549117e-09	Ctnnb1	0.978723

with pd.ExcelWriter('/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/Timespecifc_DEanalysis.xlsx') as writer: f_df_E16_5.to_excel(writer, sheet_name='Female_E16.5') f_df_E15_5.to_excel(writer, sheet_name='Female_E15.5') f_df_E14_5.to_excel(writer, sheet_name='Female_E14.5') f_df_E13_5.to_excel(writer, sheet_name='Female_E13.5') f_df_E12_5.to_excel(writer, sheet_name='Female_E12.5') f_df_E11_5.to_excel(writer, sheet_name='Female_E11.5') m_df_E16_5.to_excel(writer, sheet_name='Male_E16.5') m_df_E15_5.to_excel(writer, sheet_name='Male_E15.5') m_df_E14_5.to_excel(writer, sheet_name='Male_E14.5') m_df_E13_5.to_excel(writer, sheet_name='Male_E13.5') m_df_E12_5.to_excel(writer, sheet_name='Male_E12.5') m_df_E11_5.to_excel(writer, sheet_name='Male_E11.5')

sc.pl.DotPlot(gcAnndata, 
                 pd.concat([f_df_E11_5[1:20].names, f_df_E12_5[1:20].names, f_df_E13_5[1:20].names, f_df_E14_5[1:20].names, f_df_E15_5[1:20].names, f_df_E16_5[1:20].names, 
                            m_df_E11_5[1:20].names, m_df_E12_5[1:20].names, m_df_E13_5[1:20].names, m_df_E14_5[1:20].names, m_df_E15_5[1:20].names, m_df_E16_5[1:20].names], axis = 0).reset_index(drop=True),
                 cmap=heatcolors_wr,
                 groupby="stage_sex",
                 #swap_axes = False, 
                 #dendrogram = False,
                 standard_scale = "var").add_totals().show()

GO_f11_5 = sc.queries.enrich(f_df_E11_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_f12_5 = sc.queries.enrich(f_df_E12_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_f13_5 = sc.queries.enrich(f_df_E13_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_f14_5 = sc.queries.enrich(f_df_E14_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_f15_5 = sc.queries.enrich(f_df_E15_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_f16_5 = sc.queries.enrich(f_df_E16_5.dropna(axis=0)["names"].to_list(), org="mmusculus")

GO_m11_5 = sc.queries.enrich(m_df_E11_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_m12_5 = sc.queries.enrich(m_df_E12_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_m13_5 = sc.queries.enrich(m_df_E13_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_m14_5 = sc.queries.enrich(m_df_E14_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_m15_5 = sc.queries.enrich(m_df_E15_5.dropna(axis=0)["names"].to_list(), org="mmusculus") GO_m16_5 = sc.queries.enrich(m_df_E16_5.dropna(axis=0)["names"].to_list(), org="mmusculus")

with pd.ExcelWriter('/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/GO_analysis.xlsx') as writer: GO_f11_5.to_excel(writer, sheet_name='GO_f11_5') GO_f12_5.to_excel(writer, sheet_name='GO_f12_5') GO_f13_5.to_excel(writer, sheet_name='GO_f13_5') GO_f14_5.to_excel(writer, sheet_name='GO_f14_5') GO_f15_5.to_excel(writer, sheet_name='GO_f15_5') GO_f16_5.to_excel(writer, sheet_name='GO_f16_5') GO_m11_5.to_excel(writer, sheet_name='GO_m11_5') GO_m12_5.to_excel(writer, sheet_name='GO_m12_5') GO_m13_5.to_excel(writer, sheet_name='GO_m13_5') GO_m14_5.to_excel(writer, sheet_name='GO_m14_5') GO_m15_5.to_excel(writer, sheet_name='GO_m15_5') GO_m16_5.to_excel(writer, sheet_name='GO_m16_5')

Male v Female gslist

sc.tl.rank_genes_groups(gcAnndata, 'stage_sex', method='wilcoxon')

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['rank_genes_groups']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:01)

sc.pl.rank_genes_groups(gcAnndata, n_genes=25, sharey=False, gene_symbols="external_gene_name")

result = gcAnndata.uns['rank_genes_groups']
groups = result['names'].dtype.names
pd.DataFrame(
    {group + '_' + key[:1]: result[key][group]
    for group in groups for key in ['names', 'scores', 'logfoldchanges', 'pvals_adj']}).head(50)

	female_E10.5_n	female_E10.5_s	female_E10.5_l	female_E10.5_p	female_E11.5_n	female_E11.5_s	female_E11.5_l	female_E11.5_p	female_E12.5_n	female_E12.5_s	female_E12.5_l	female_E12.5_p	female_E13.5_n	female_E13.5_s	female_E13.5_l	female_E13.5_p	female_E14.5_n	female_E14.5_s	female_E14.5_l	female_E14.5_p	female_E15.5_n	female_E15.5_s	female_E15.5_l	female_E15.5_p	female_E16.5_n	female_E16.5_s	female_E16.5_l	female_E16.5_p	male_E10.5_n	male_E10.5_s	male_E10.5_l	male_E10.5_p	male_E11.5_n	male_E11.5_s	male_E11.5_l	male_E11.5_p	male_E12.5_n	male_E12.5_s	male_E12.5_l	male_E12.5_p	male_E13.5_n	male_E13.5_s	male_E13.5_l	male_E13.5_p	male_E14.5_n	male_E14.5_s	male_E14.5_l	male_E14.5_p	male_E15.5_n	male_E15.5_s	male_E15.5_l	male_E15.5_p	male_E16.5_n	male_E16.5_s	male_E16.5_l	male_E16.5_p
0	ENSMUSG00000086290	10.071825	356.789215	5.194648e-20	ENSMUSG00000049539	9.802875	328.357483	2.317000e-18	ENSMUSG00000068048	10.435003	inf	3.633613e-21	ENSMUSG00000015053	8.568956	634.627197	2.211137e-13	ENSMUSG00000009549	11.258389	inf	4.458666e-25	ENSMUSG00000085601	9.520860	inf	5.195239e-18	ENSMUSG00000016427	12.876844	inf	6.433672e-34	ENSMUSG00000050621	7.388151	90.319962	1.050828e-09	ENSMUSG00000091405	9.368430	121.183609	8.214427e-17	ENSMUSG00000066652	10.129660	inf	8.640414e-20	ENSMUSG00000040726	8.459110	227.576523	5.704808e-13	ENSMUSG00000060985	11.299863	inf	2.317641e-25	ENSMUSG00000017009	11.332695	inf	1.913708e-25	ENSMUSG00000031765	12.796465	inf	6.055304e-34
1	ENSMUSG00000022114	9.996903	161.074356	8.323366e-20	ENSMUSG00000091405	9.613456	166.443558	7.427192e-18	ENSMUSG00000006200	10.269109	inf	1.027970e-20	ENSMUSG00000002324	8.430614	inf	3.640409e-13	ENSMUSG00000079184	11.165549	inf	4.622438e-25	ENSMUSG00000079507	9.502802	79.002922	5.407765e-18	ENSMUSG00000096210	12.460629	inf	5.183393e-32	ENSMUSG00000090733	7.307340	NaN	1.442389e-09	ENSMUSG00000039202	9.362884	286.835846	8.214427e-17	ENSMUSG00000038793	9.385757	inf	6.613246e-17	ENSMUSG00000046323	8.259953	NaN	1.315307e-12	ENSMUSG00000015656	11.254965	NaN	2.317641e-25	ENSMUSG00000076617	10.747350	inf	6.456875e-23	ENSMUSG00000030720	12.726160	inf	1.119960e-33
2	ENSMUSG00000079641	9.510871	inf	4.448272e-18	ENSMUSG00000020422	9.556976	266.121613	8.557630e-18	ENSMUSG00000006585	9.891661	inf	3.193462e-19	ENSMUSG00000029848	7.799374	inf	4.391134e-11	ENSMUSG00000027879	11.157939	inf	4.622438e-25	ENSMUSG00000030041	9.383311	NaN	1.041319e-17	ENSMUSG00000031432	12.366297	inf	1.052723e-31	ENSMUSG00000053332	7.038497	inf	5.696867e-09	ENSMUSG00000039678	9.204022	479.034088	1.413284e-16	ENSMUSG00000063856	9.227533	NaN	1.954609e-16	ENSMUSG00000024521	8.230549	216.246826	1.315307e-12	ENSMUSG00000032399	11.184193	NaN	3.439491e-25	ENSMUSG00000064215	10.645263	inf	1.294905e-22	ENSMUSG00000028784	12.590128	inf	5.066626e-33
3	ENSMUSG00000057322	9.343737	inf	1.640859e-17	ENSMUSG00000031691	9.503186	322.096161	9.954063e-18	ENSMUSG00000001270	9.599442	NaN	4.254817e-18	ENSMUSG00000070858	7.443162	399.929077	5.203667e-10	ENSMUSG00000042682	11.024386	inf	1.543055e-24	ENSMUSG00000029848	9.354879	inf	1.225165e-17	ENSMUSG00000031397	12.289491	inf	1.985609e-31	ENSMUSG00000034892	7.024236	NaN	5.696867e-09	ENSMUSG00000063021	9.194911	62.954388	1.413284e-16	ENSMUSG00000030246	9.083806	NaN	5.549853e-16	ENSMUSG00000041359	7.371583	inf	8.008315e-10	ENSMUSG00000052374	11.123314	inf	4.512018e-25	ENSMUSG00000058550	10.347286	NaN	2.278925e-21	ENSMUSG00000000730	12.507071	inf	1.032946e-32
4	ENSMUSG00000104960	9.299936	131.445847	2.288909e-17	ENSMUSG00000101355	9.488202	43.106407	9.954063e-18	ENSMUSG00000010760	9.426699	inf	1.792162e-17	ENSMUSG00000007872	7.014052	NaN	9.804120e-09	ENSMUSG00000000346	10.993567	inf	1.737889e-24	ENSMUSG00000005470	9.133571	inf	6.378795e-17	ENSMUSG00000078938	12.128869	756.731567	1.123250e-30	ENSMUSG00000067288	6.969834	NaN	7.351964e-09	ENSMUSG00000068457	9.186591	72.683029	1.413284e-16	ENSMUSG00000054405	9.034102	inf	7.002407e-16	ENSMUSG00000030246	7.340220	NaN	8.008315e-10	ENSMUSG00000022234	11.105812	NaN	4.512018e-25	ENSMUSG00000056155	10.201117	739.700562	8.300503e-21	ENSMUSG00000024164	12.428590	576.699585	2.419528e-32
5	ENSMUSG00000034892	9.241920	NaN	3.417679e-17	ENSMUSG00000061991	9.468607	35.604073	1.000827e-17	ENSMUSG00000005566	9.284775	NaN	5.718710e-17	ENSMUSG00000057762	6.588669	23.610441	1.566121e-07	ENSMUSG00000050608	10.972259	inf	1.833594e-24	ENSMUSG00000061232	9.124734	inf	6.620344e-17	ENSMUSG00000051592	11.921399	721.021729	1.077026e-29	ENSMUSG00000025362	6.914375	NaN	7.351964e-09	ENSMUSG00000051391	9.163614	524.181458	1.413284e-16	ENSMUSG00000026520	8.991854	inf	8.578802e-16	ENSMUSG00000035557	7.313953	454.106567	8.008315e-10	ENSMUSG00000000902	11.085265	inf	4.512018e-25	ENSMUSG00000052374	10.068204	inf	2.694744e-20	ENSMUSG00000000739	12.419762	636.991089	2.542995e-32
6	ENSMUSG00000069309	9.221172	74.217354	3.889006e-17	ENSMUSG00000039678	9.452085	485.393005	1.004694e-17	ENSMUSG00000095180	9.183945	NaN	1.143545e-16	ENSMUSG00000048450	6.485534	365.052887	2.674526e-07	ENSMUSG00000028618	10.939536	inf	2.255945e-24	ENSMUSG00000011349	9.109365	inf	7.310792e-17	ENSMUSG00000027855	11.702137	inf	1.253128e-28	ENSMUSG00000108414	6.913319	544.890747	7.351964e-09	ENSMUSG00000066232	9.162029	358.561188	1.413284e-16	ENSMUSG00000060461	8.710612	NaN	9.142230e-15	ENSMUSG00000032346	7.311209	143.366837	8.008315e-10	ENSMUSG00000025613	11.078416	NaN	4.512018e-25	ENSMUSG00000026354	10.011194	548.569092	4.116838e-20	ENSMUSG00000020799	12.392293	459.406097	3.245618e-32
7	ENSMUSG00000009927	9.105907	NaN	9.056999e-17	ENSMUSG00000011256	9.206187	482.425598	8.234448e-17	ENSMUSG00000028640	9.179759	718.805115	1.143545e-16	ENSMUSG00000031146	6.097429	inf	1.956871e-06	ENSMUSG00000047260	10.905293	inf	2.878165e-24	ENSMUSG00000030760	9.096302	333.317230	7.692398e-17	ENSMUSG00000071103	11.526855	541.904663	7.305648e-28	ENSMUSG00000009927	6.908566	NaN	7.351964e-09	ENSMUSG00000026276	9.156879	37.850594	1.413284e-16	ENSMUSG00000054766	8.631500	NaN	1.602667e-14	ENSMUSG00000066705	7.163016	653.171387	1.671072e-09	ENSMUSG00000039756	11.068904	inf	4.512018e-25	ENSMUSG00000028378	9.591575	489.576355	2.296073e-18	ENSMUSG00000059625	12.198709	inf	2.907173e-31
8	ENSMUSG00000061983	9.075554	NaN	1.140374e-16	ENSMUSG00000031523	9.196582	197.717590	8.234448e-17	ENSMUSG00000015176	9.151983	inf	1.315088e-16	ENSMUSG00000022884	6.078790	inf	1.972324e-06	ENSMUSG00000051159	10.873331	inf	3.633857e-24	ENSMUSG00000022429	9.027143	616.149963	1.286589e-16	ENSMUSG00000020059	11.484469	inf	1.152905e-27	ENSMUSG00000092203	6.890607	inf	7.351964e-09	ENSMUSG00000031523	9.144202	295.277374	1.413284e-16	ENSMUSG00000059552	8.557773	inf	2.471716e-14	ENSMUSG00000047407	7.148118	376.947021	1.693443e-09	ENSMUSG00000035960	11.060153	inf	4.512018e-25	ENSMUSG00000044595	9.421871	NaN	1.042514e-17	ENSMUSG00000025401	12.137234	732.697937	5.747749e-31
9	ENSMUSG00000074578	9.015616	466.001648	1.763852e-16	ENSMUSG00000051391	9.182366	451.175049	8.234448e-17	ENSMUSG00000034708	9.136764	inf	1.362531e-16	ENSMUSG00000031158	6.000506	inf	2.974997e-06	ENSMUSG00000026239	10.835662	inf	4.029794e-24	ENSMUSG00000051159	9.015616	inf	1.337144e-16	ENSMUSG00000020774	11.233019	228.363022	1.449741e-26	ENSMUSG00000079641	6.876875	inf	7.479258e-09	ENSMUSG00000049539	9.125583	278.133148	1.510795e-16	ENSMUSG00000016344	8.556116	inf	2.471716e-14	ENSMUSG00000063856	6.905052	NaN	8.855144e-09	ENSMUSG00000019139	11.052543	NaN	4.512018e-25	ENSMUSG00000051316	9.370165	inf	1.533412e-17	ENSMUSG00000018012	12.075758	488.381378	1.112428e-30
10	ENSMUSG00000032249	8.982574	234.360962	2.074303e-16	ENSMUSG00000045817	9.180829	105.811790	8.234448e-17	ENSMUSG00000010660	9.090343	inf	1.754267e-16	ENSMUSG00000021361	5.856365	376.572937	5.892703e-06	ENSMUSG00000085601	10.835281	inf	4.029794e-24	ENSMUSG00000022837	8.999479	inf	1.412368e-16	ENSMUSG00000112920	11.097893	24.273617	6.180696e-26	ENSMUSG00000047675	6.863670	NaN	7.479258e-09	ENSMUSG00000011256	8.916013	527.337646	9.304552e-16	ENSMUSG00000051695	8.534578	inf	2.707731e-14	ENSMUSG00000000579	6.701974	165.935944	2.721161e-08	ENSMUSG00000006273	11.010308	inf	6.560788e-25	ENSMUSG00000024767	9.228966	NaN	4.821633e-17	ENSMUSG00000026809	12.012321	309.631592	2.160693e-30
11	ENSMUSG00000093674	8.928400	NaN	3.155766e-16	ENSMUSG00000037857	9.154319	204.273666	9.652163e-17	ENSMUSG00000051695	9.089582	inf	1.754267e-16	ENSMUSG00000006369	5.785537	inf	8.055165e-06	ENSMUSG00000024099	10.829955	inf	4.029794e-24	ENSMUSG00000047220	8.893436	576.618225	3.358933e-16	ENSMUSG00000005883	10.998141	636.804321	1.795593e-25	ENSMUSG00000063457	6.835149	NaN	8.633094e-09	ENSMUSG00000059436	8.898582	155.717178	9.378932e-16	ENSMUSG00000018293	8.507241	NaN	3.142952e-14	ENSMUSG00000054196	6.421663	102.897881	1.240920e-07	ENSMUSG00000058550	10.979108	NaN	8.498852e-25	ENSMUSG00000005413	9.209079	inf	5.357617e-17	ENSMUSG00000036526	11.968175	676.047119	3.346984e-30
12	ENSMUSG00000101972	8.775867	144.227432	1.025991e-15	ENSMUSG00000060206	9.112823	239.524078	1.307340e-16	ENSMUSG00000037169	8.823618	inf	1.804993e-15	ENSMUSG00000096472	5.708081	495.721375	1.083007e-05	ENSMUSG00000051455	10.828814	inf	4.029794e-24	ENSMUSG00000024786	8.891515	554.625244	3.358933e-16	ENSMUSG00000009596	10.873851	inf	6.135619e-25	ENSMUSG00000038900	6.828811	NaN	8.633094e-09	ENSMUSG00000026421	8.896602	132.971664	9.378932e-16	ENSMUSG00000004864	8.495644	inf	3.206066e-14	ENSMUSG00000017009	6.372658	NaN	1.577512e-07	ENSMUSG00000005312	10.971498	inf	8.534280e-25	ENSMUSG00000073102	9.176928	inf	6.261381e-17	ENSMUSG00000054932	11.758242	270.457031	2.836562e-29
13	ENSMUSG00000022048	8.748587	300.700470	1.270680e-15	ENSMUSG00000063021	9.104754	73.671402	1.307670e-16	ENSMUSG00000028766	8.717461	inf	4.303008e-15	ENSMUSG00000030605	5.703111	inf	1.083007e-05	ENSMUSG00000025066	10.823486	inf	4.029794e-24	ENSMUSG00000062732	8.844256	525.330139	4.758451e-16	ENSMUSG00000035540	10.715141	80.048630	3.155124e-24	ENSMUSG00000049775	6.774408	154.561874	1.102075e-08	ENSMUSG00000060126	8.854609	NaN	1.270112e-15	ENSMUSG00000005732	8.479903	inf	3.408720e-14	ENSMUSG00000026641	6.296601	498.625183	2.300722e-07	ENSMUSG00000062382	10.948668	NaN	9.189964e-25	ENSMUSG00000067764	9.051639	181.914978	1.754189e-16	ENSMUSG00000026879	11.757915	758.078735	2.836562e-29
14	ENSMUSG00000046330	8.726302	NaN	1.466212e-15	ENSMUSG00000066232	8.946458	261.630554	4.717390e-16	ENSMUSG00000004264	8.666095	NaN	6.312616e-15	ENSMUSG00000063714	5.667904	74.832603	1.197312e-05	ENSMUSG00000003824	10.811311	inf	4.295378e-24	ENSMUSG00000020097	8.825430	inf	5.356503e-16	ENSMUSG00000039217	10.540178	255.551529	1.862065e-23	ENSMUSG00000093674	6.765957	NaN	1.121633e-08	ENSMUSG00000040661	8.766264	215.987885	2.433509e-15	ENSMUSG00000061104	8.425229	102.994530	4.764738e-14	ENSMUSG00000096255	6.267982	127.499306	2.581298e-07	ENSMUSG00000024312	10.946385	inf	9.189964e-25	ENSMUSG00000000579	8.909114	242.656265	6.051297e-16	ENSMUSG00000036598	11.732081	161.754013	3.680318e-29
15	ENSMUSG00000092203	8.715160	482.455261	1.576365e-15	ENSMUSG00000039202	8.944921	197.819107	4.717390e-16	ENSMUSG00000030605	8.615489	inf	9.216473e-15	ENSMUSG00000035781	5.665005	200.785110	1.197312e-05	ENSMUSG00000031010	10.797994	inf	4.420902e-24	ENSMUSG00000029110	8.802377	NaN	6.165693e-16	ENSMUSG00000060771	10.508945	423.933319	2.410977e-23	ENSMUSG00000022114	6.752753	251.388794	1.181393e-08	ENSMUSG00000101355	8.759926	44.786339	2.433509e-15	ENSMUSG00000003873	8.425229	inf	4.764738e-14	ENSMUSG00000052374	6.203295	inf	3.403922e-07	ENSMUSG00000029614	10.946005	NaN	9.189964e-25	ENSMUSG00000053909	8.897182	161.731735	6.383706e-16	ENSMUSG00000029223	11.698728	inf	5.168798e-29
16	ENSMUSG00000108414	8.669823	310.604126	2.235114e-15	ENSMUSG00000022443	8.943000	441.339966	4.717390e-16	ENSMUSG00000029591	8.536727	inf	1.719792e-14	ENSMUSG00000041765	5.378793	324.426788	4.973215e-05	ENSMUSG00000022432	10.794188	inf	4.420902e-24	ENSMUSG00000032854	8.786624	525.596558	6.526723e-16	ENSMUSG00000045106	10.502572	220.560959	2.506826e-23	ENSMUSG00000039001	6.729513	inf	1.334994e-08	ENSMUSG00000069267	8.759926	43.575199	2.433509e-15	ENSMUSG00000028945	8.385467	536.316223	6.293053e-14	ENSMUSG00000038793	6.149977	812.830566	4.434750e-07	ENSMUSG00000037058	10.930024	inf	1.031627e-24	ENSMUSG00000060985	8.761286	inf	2.043664e-15	ENSMUSG00000048997	11.683032	669.512817	6.102944e-29
17	ENSMUSG00000031245	8.630249	402.964752	2.846467e-15	ENSMUSG00000025278	8.911879	227.916290	5.902262e-16	ENSMUSG00000021953	8.497156	inf	2.285527e-14	ENSMUSG00000015217	5.378379	326.979675	4.973215e-05	ENSMUSG00000039105	10.787339	inf	4.420902e-24	ENSMUSG00000028212	8.763955	171.921585	7.676233e-16	ENSMUSG00000036499	10.489824	286.133453	2.790538e-23	ENSMUSG00000060636	6.602222	NaN	2.382306e-08	ENSMUSG00000035203	8.714367	147.499298	3.439458e-15	ENSMUSG00000016921	8.365170	NaN	7.061307e-14	ENSMUSG00000060461	6.065688	NaN	7.133456e-07	ENSMUSG00000041438	10.893877	NaN	1.379583e-24	ENSMUSG00000031880	8.738085	inf	2.390609e-15	ENSMUSG00000021681	11.537844	inf	2.951505e-28
18	ENSMUSG00000046402	8.549563	214.926605	5.293363e-15	ENSMUSG00000099583	8.905731	54.436337	5.910371e-16	ENSMUSG00000029622	8.453780	inf	3.142902e-14	ENSMUSG00000025920	5.267787	202.640869	7.816256e-05	ENSMUSG00000028648	10.786959	inf	4.420902e-24	ENSMUSG00000005683	8.758961	NaN	7.872680e-16	ENSMUSG00000031431	10.410469	inf	6.029813e-23	ENSMUSG00000040459	6.525637	inf	3.676312e-08	ENSMUSG00000089774	8.700897	210.170532	3.669453e-15	ENSMUSG00000055044	8.324164	inf	9.464276e-14	ENSMUSG00000095677	6.054711	191.888718	7.264747e-07	ENSMUSG00000037742	10.893497	NaN	1.379583e-24	ENSMUSG00000045877	8.659199	139.925888	4.373739e-15	ENSMUSG00000039661	11.498931	527.723938	4.418717e-28
19	ENSMUSG00000032607	8.546490	inf	5.293363e-15	ENSMUSG00000070047	8.893821	482.350708	6.250892e-16	ENSMUSG00000031169	8.416111	inf	4.120339e-14	ENSMUSG00000064367	5.252876	NaN	8.129842e-05	ENSMUSG00000030180	10.778969	inf	4.581098e-24	ENSMUSG00000024841	8.744745	inf	8.764478e-16	ENSMUSG00000045193	10.352467	607.291809	1.066123e-22	ENSMUSG00000090862	6.511376	NaN	3.941836e-08	ENSMUSG00000021255	8.694559	324.045776	3.686182e-15	ENSMUSG00000006442	8.290614	inf	1.188579e-13	ENSMUSG00000026305	6.010802	309.216888	8.686401e-07	ENSMUSG00000028378	10.875995	inf	1.588169e-24	ENSMUSG00000025357	8.648592	410.290436	4.493540e-15	ENSMUSG00000040701	11.490102	511.874268	4.819098e-28
20	ENSMUSG00000087166	8.520747	329.701385	6.216030e-15	ENSMUSG00000101972	8.864236	174.659836	7.766882e-16	ENSMUSG00000060860	8.387955	374.219116	4.987720e-14	ENSMUSG00000028843	5.201516	359.669159	9.855447e-05	ENSMUSG00000022837	10.744724	inf	6.326898e-24	ENSMUSG00000002109	8.711702	673.440430	1.111988e-15	ENSMUSG00000112858	10.197263	466.076385	4.745285e-22	ENSMUSG00000008683	6.488136	NaN	4.182098e-08	ENSMUSG00000074578	8.688617	466.598541	3.699201e-15	ENSMUSG00000056201	8.285230	inf	1.188579e-13	ENSMUSG00000025403	5.989632	453.384766	9.680962e-07	ENSMUSG00000002524	10.870667	NaN	1.603510e-24	ENSMUSG00000032380	8.646604	238.079346	4.493540e-15	ENSMUSG00000036912	11.464923	inf	6.163346e-28
21	ENSMUSG00000085525	8.487320	15.317883	8.140677e-15	ENSMUSG00000054753	8.841567	153.894287	9.084155e-16	ENSMUSG00000034165	8.348763	inf	6.264826e-14	ENSMUSG00000027239	5.190746	357.929596	9.855447e-05	ENSMUSG00000040785	10.735973	inf	6.639811e-24	ENSMUSG00000050035	8.629480	499.859344	2.139318e-15	ENSMUSG00000060445	10.177822	238.629791	5.732462e-22	ENSMUSG00000046330	6.454861	NaN	4.879861e-08	ENSMUSG00000061983	8.637511	NaN	5.529365e-15	ENSMUSG00000026305	8.221029	inf	1.941891e-13	ENSMUSG00000025739	5.958269	22.707628	1.148462e-06	ENSMUSG00000019471	10.866101	NaN	1.609160e-24	ENSMUSG00000051965	8.611469	142.622147	5.874150e-15	ENSMUSG00000049154	11.452170	150.155563	7.037466e-28
22	ENSMUSG00000087590	8.446209	137.487274	1.117816e-14	ENSMUSG00000026923	8.820820	250.488373	1.046042e-15	ENSMUSG00000002985	8.347242	inf	6.264826e-14	ENSMUSG00000068048	5.177492	NaN	1.035172e-04	ENSMUSG00000029848	10.721895	inf	7.396200e-24	ENSMUSG00000032387	8.622949	inf	2.228455e-15	ENSMUSG00000025037	10.130975	646.860107	9.166689e-22	ENSMUSG00000025290	6.423170	NaN	5.434601e-08	ENSMUSG00000086290	8.624834	215.369080	5.908971e-15	ENSMUSG00000064368	8.148129	255.045242	3.402525e-13	ENSMUSG00000070436	5.861826	341.220825	1.837632e-06	ENSMUSG00000019432	10.825769	NaN	2.392548e-24	ENSMUSG00000060376	8.600200	323.075592	6.240622e-15	ENSMUSG00000038080	11.427973	inf	8.785742e-28
23	ENSMUSG00000090862	8.400872	NaN	1.617896e-14	ENSMUSG00000069267	8.783550	43.118755	1.397428e-15	ENSMUSG00000030541	8.345340	inf	6.264826e-14	ENSMUSG00000022982	5.133587	NaN	1.203833e-04	ENSMUSG00000030041	10.692597	NaN	9.725946e-24	ENSMUSG00000009291	8.618338	inf	2.247520e-15	ENSMUSG00000073411	9.970034	inf	4.197316e-21	ENSMUSG00000058600	6.380388	NaN	6.530132e-08	ENSMUSG00000054753	8.616118	169.961548	6.110630e-15	ENSMUSG00000021377	8.062805	inf	6.577312e-13	ENSMUSG00000025491	5.848888	NaN	1.940435e-06	ENSMUSG00000030357	10.792666	NaN	3.123908e-24	ENSMUSG00000074397	8.517006	inf	1.238162e-14	ENSMUSG00000038375	11.370420	608.900269	1.573419e-27
24	ENSMUSG00000067288	8.393956	NaN	1.686929e-14	ENSMUSG00000021255	8.762803	288.813995	1.613073e-15	ENSMUSG00000003528	8.286743	inf	9.857867e-14	ENSMUSG00000079641	5.092581	inf	1.411153e-04	ENSMUSG00000008892	10.678518	inf	1.086671e-23	ENSMUSG00000028273	8.577611	457.123230	3.061187e-15	ENSMUSG00000000563	9.953780	NaN	4.895866e-21	ENSMUSG00000032607	6.379331	inf	6.530132e-08	ENSMUSG00000025278	8.593142	287.445648	7.167252e-15	ENSMUSG00000009013	8.057835	NaN	6.577312e-13	ENSMUSG00000028044	5.801451	284.541351	2.442195e-06	ENSMUSG00000071644	10.791905	NaN	3.123908e-24	ENSMUSG00000032047	8.491484	460.753967	1.489595e-14	ENSMUSG00000058672	11.143810	318.193573	1.710940e-26
25	ENSMUSG00000047675	8.357071	NaN	2.195758e-14	ENSMUSG00000001910	8.746666	297.883850	1.789603e-15	ENSMUSG00000047945	8.254022	inf	1.247247e-13	ENSMUSG00000048583	5.024652	7.491227	1.906964e-04	ENSMUSG00000066551	10.674334	NaN	1.093047e-23	ENSMUSG00000027879	8.563011	inf	3.264664e-15	ENSMUSG00000089719	9.901514	18.310062	8.113770e-21	ENSMUSG00000041841	6.375634	NaN	6.530132e-08	ENSMUSG00000026773	8.582445	126.583672	7.563799e-15	ENSMUSG00000042367	7.967953	inf	1.313797e-12	ENSMUSG00000067148	5.768520	inf	2.731135e-06	ENSMUSG00000064215	10.790003	inf	3.123908e-24	ENSMUSG00000022652	8.421216	inf	2.544961e-14	ENSMUSG00000025372	11.072851	inf	3.562000e-26
26	ENSMUSG00000079259	8.328256	387.264221	2.757410e-14	ENSMUSG00000032249	8.734756	172.507019	1.850906e-15	ENSMUSG00000020307	8.233475	inf	1.426185e-13	ENSMUSG00000046814	5.000215	135.967194	2.064037e-04	ENSMUSG00000030417	10.646937	inf	1.413131e-23	ENSMUSG00000051455	8.561858	228.851288	3.264664e-15	ENSMUSG00000020664	9.898646	485.481781	8.272529e-21	ENSMUSG00000057278	6.372465	inf	6.530132e-08	ENSMUSG00000070047	8.574125	497.344666	7.675970e-15	ENSMUSG00000021963	7.958841	inf	1.361868e-12	ENSMUSG00000026672	5.741469	179.000793	3.131994e-06	ENSMUSG00000050708	10.786578	NaN	3.123908e-24	ENSMUSG00000020661	8.398346	inf	2.860030e-14	ENSMUSG00000020661	11.067946	inf	3.689349e-26
27	ENSMUSG00000053332	8.307123	inf	3.243923e-14	ENSMUSG00000045671	8.730913	98.047829	1.850906e-15	ENSMUSG00000059552	8.194283	inf	1.906336e-13	ENSMUSG00000062683	4.999386	inf	2.064037e-04	ENSMUSG00000000088	10.643514	inf	1.413700e-23	ENSMUSG00000049755	8.549179	inf	3.547132e-15	ENSMUSG00000025090	9.862315	346.131622	1.156653e-20	ENSMUSG00000007836	6.351866	126.879761	6.815512e-08	ENSMUSG00000061991	8.569768	49.910564	7.675970e-15	ENSMUSG00000004264	7.894640	NaN	2.132901e-12	ENSMUSG00000018899	5.736372	423.486328	3.131994e-06	ENSMUSG00000068039	10.757280	NaN	4.141206e-24	ENSMUSG00000023966	8.396688	344.606628	2.860030e-14	ENSMUSG00000031825	11.047018	499.898102	4.500844e-26
28	ENSMUSG00000031939	8.288297	407.572479	3.685612e-14	ENSMUSG00000094338	8.730145	62.994644	1.850906e-15	ENSMUSG00000020733	8.184772	inf	1.991966e-13	ENSMUSG00000064368	4.988203	94.684120	2.150697e-04	ENSMUSG00000032409	10.636284	inf	1.475072e-23	ENSMUSG00000022940	8.534964	451.675812	3.958130e-15	ENSMUSG00000043410	9.800170	450.928162	2.034093e-20	ENSMUSG00000079435	6.343415	NaN	6.967496e-08	ENSMUSG00000037857	8.568183	203.560730	7.675970e-15	ENSMUSG00000036438	7.894226	NaN	2.132901e-12	ENSMUSG00000040296	5.700304	197.916733	3.650971e-06	ENSMUSG00000024966	10.751193	NaN	4.181224e-24	ENSMUSG00000038845	8.360891	NaN	3.765714e-14	ENSMUSG00000067338	11.026417	inf	5.387910e-26
29	ENSMUSG00000093483	8.234507	33.229862	5.376978e-14	ENSMUSG00000035621	8.726686	56.694969	1.850906e-15	ENSMUSG00000018677	8.174118	NaN	2.103555e-13	ENSMUSG00000020644	4.956310	235.792862	2.443664e-04	ENSMUSG00000029148	10.631718	NaN	1.497476e-23	ENSMUSG00000024905	8.505379	707.554016	4.899805e-15	ENSMUSG00000005881	9.769575	inf	2.683607e-20	ENSMUSG00000041453	6.341831	NaN	6.967496e-08	ENSMUSG00000042348	8.530944	119.847816	1.024527e-14	ENSMUSG00000045394	7.884699	inf	2.167894e-12	ENSMUSG00000054612	5.698736	284.307556	3.650971e-06	ENSMUSG00000030007	10.749671	NaN	4.181224e-24	ENSMUSG00000053398	8.313494	inf	5.392634e-14	ENSMUSG00000004032	11.013664	inf	6.153037e-26
30	ENSMUSG00000028367	8.205306	inf	6.581219e-14	ENSMUSG00000050271	8.705555	82.306290	2.158553e-15	ENSMUSG00000002870	8.146342	NaN	2.562044e-13	ENSMUSG00000042745	4.954238	91.233078	2.443664e-04	ENSMUSG00000025480	10.611933	inf	1.749585e-23	ENSMUSG00000025480	8.493084	inf	5.260180e-15	ENSMUSG00000028957	9.768619	inf	2.686660e-20	ENSMUSG00000030539	6.330739	579.062561	7.380343e-08	ENSMUSG00000022443	8.500440	431.649628	1.290071e-14	ENSMUSG00000058135	7.883871	inf	2.167894e-12	ENSMUSG00000021273	5.693247	NaN	3.717247e-06	ENSMUSG00000052833	10.747007	NaN	4.181224e-24	ENSMUSG00000025081	8.311836	552.779358	5.392634e-14	ENSMUSG00000053398	10.992083	inf	7.681351e-26
31	ENSMUSG00000070526	8.162659	130.704010	8.896516e-14	ENSMUSG00000052609	8.690187	317.689514	2.394289e-15	ENSMUSG00000042367	8.028389	inf	6.534872e-13	ENSMUSG00000009905	4.953825	129.755112	2.443664e-04	ENSMUSG00000030086	10.611172	inf	1.749585e-23	ENSMUSG00000000346	8.480021	inf	5.813932e-15	ENSMUSG00000020132	9.758739	248.763504	2.913506e-20	ENSMUSG00000012848	6.305387	NaN	8.454181e-08	ENSMUSG00000026398	8.486177	98.802994	1.412998e-14	ENSMUSG00000102252	7.851563	707.585388	2.718764e-12	ENSMUSG00000053654	5.612879	354.582245	4.956913e-06	ENSMUSG00000062867	10.719612	NaN	5.448874e-24	ENSMUSG00000023092	8.258804	325.229919	7.988535e-14	ENSMUSG00000023043	10.969520	315.747803	9.775885e-26
32	ENSMUSG00000042699	8.161890	295.865570	8.896516e-14	ENSMUSG00000058385	8.678275	76.707970	2.578189e-15	ENSMUSG00000020717	8.009746	inf	7.375379e-13	ENSMUSG00000027984	4.898322	227.383148	2.966161e-04	ENSMUSG00000032065	10.586820	inf	2.201121e-23	ENSMUSG00000026027	8.476947	409.050812	5.897622e-15	ENSMUSG00000026894	9.713803	366.516449	4.460491e-20	ENSMUSG00000028936	6.301161	inf	8.568923e-08	ENSMUSG00000081683	8.468350	61.280212	1.587345e-14	ENSMUSG00000015176	7.840380	NaN	2.882139e-12	ENSMUSG00000066652	5.545447	214.730942	6.748148e-06	ENSMUSG00000037958	10.694880	inf	6.901372e-24	ENSMUSG00000038803	8.215053	140.890274	1.122603e-13	ENSMUSG00000036564	10.944667	457.607666	1.243548e-25
33	ENSMUSG00000030539	8.161121	303.485504	8.896516e-14	ENSMUSG00000070780	8.668670	303.204315	2.722706e-15	ENSMUSG00000040945	8.003277	inf	7.544870e-13	ENSMUSG00000031311	4.825008	inf	3.849746e-04	ENSMUSG00000019054	10.581493	inf	2.205741e-23	ENSMUSG00000022404	8.432378	inf	8.339405e-15	ENSMUSG00000113902	9.688626	345.136688	5.531998e-20	ENSMUSG00000049517	6.285844	NaN	9.205821e-08	ENSMUSG00000070733	8.465577	146.090942	1.587345e-14	ENSMUSG00000041891	7.823398	534.219482	3.202030e-12	ENSMUSG00000029447	5.517612	NaN	7.579337e-06	ENSMUSG00000059447	10.687270	inf	7.271224e-24	ENSMUSG00000007564	8.210743	NaN	1.135253e-13	ENSMUSG00000029762	10.923412	494.059357	1.521192e-25
34	ENSMUSG00000041841	8.156895	NaN	9.098117e-14	ENSMUSG00000030539	8.659064	347.633911	2.877550e-15	ENSMUSG00000028333	7.940115	NaN	1.222005e-12	ENSMUSG00000054717	4.789802	NaN	4.418654e-04	ENSMUSG00000042043	10.581113	595.976624	2.205741e-23	ENSMUSG00000037315	8.422772	644.796021	8.875926e-15	ENSMUSG00000034210	9.666955	524.551025	6.733448e-20	ENSMUSG00000071072	6.273168	inf	9.603650e-08	ENSMUSG00000052609	8.460823	321.274567	1.606175e-14	ENSMUSG00000027405	7.781149	NaN	4.347847e-12	ENSMUSG00000059796	5.505851	NaN	8.019694e-06	ENSMUSG00000021037	10.679660	NaN	7.667088e-24	ENSMUSG00000026113	8.118931	278.225769	2.371024e-13	ENSMUSG00000011589	10.875670	inf	2.452028e-25
35	ENSMUSG00000028788	8.150363	inf	9.484703e-14	ENSMUSG00000034275	8.645233	154.899399	3.114477e-15	ENSMUSG00000029249	7.927559	inf	1.309917e-12	ENSMUSG00000037235	4.764121	148.231796	4.725005e-04	ENSMUSG00000024844	10.571600	NaN	2.373539e-23	ENSMUSG00000028955	8.422388	inf	8.875926e-15	ENSMUSG00000022432	9.653889	inf	7.534468e-20	ENSMUSG00000079259	6.252569	730.939697	1.062613e-07	ENSMUSG00000022048	8.372479	341.714539	3.318341e-14	ENSMUSG00000020358	7.693753	582.109680	8.283238e-12	ENSMUSG00000060703	5.473703	88.857765	9.169237e-06	ENSMUSG00000005656	10.671289	inf	8.157189e-24	ENSMUSG00000025959	8.091752	145.843750	2.830224e-13	ENSMUSG00000040752	10.873055	313.199219	2.504118e-25
36	ENSMUSG00000026873	8.146137	506.340240	9.702192e-14	ENSMUSG00000069302	8.643696	17.135046	3.114477e-15	ENSMUSG00000024827	7.922612	815.749451	1.309917e-12	ENSMUSG00000010760	4.737198	411.665436	5.213936e-04	ENSMUSG00000022940	10.559044	inf	2.640087e-23	ENSMUSG00000052525	8.408556	372.759521	9.765646e-15	ENSMUSG00000030309	9.651977	inf	7.619034e-20	ENSMUSG00000054766	6.245174	NaN	1.093116e-07	ENSMUSG00000010660	8.359010	inf	3.595885e-14	ENSMUSG00000033845	7.692096	inf	8.283238e-12	ENSMUSG00000069053	5.463510	302.936310	9.596350e-06	ENSMUSG00000043716	10.635142	NaN	1.170383e-23	ENSMUSG00000025403	8.074184	inf	3.196281e-13	ENSMUSG00000020265	10.838392	inf	3.604583e-25
37	ENSMUSG00000038900	8.127695	NaN	1.116180e-13	ENSMUSG00000059901	8.621027	187.587006	3.697427e-15	ENSMUSG00000020349	7.918808	363.451874	1.309917e-12	ENSMUSG00000034807	4.729328	354.218475	5.241468e-04	ENSMUSG00000011349	10.552576	inf	2.753918e-23	ENSMUSG00000073411	8.398951	inf	1.048195e-14	ENSMUSG00000037363	9.629987	262.545654	9.300546e-20	ENSMUSG00000059291	6.239364	NaN	1.120826e-07	ENSMUSG00000061013	8.356633	139.606384	3.595885e-14	ENSMUSG00000037169	7.657718	inf	1.054413e-11	ENSMUSG00000032380	5.458414	151.671860	9.780907e-06	ENSMUSG00000033628	10.629436	inf	1.211516e-23	ENSMUSG00000037772	8.036068	NaN	4.270124e-13	ENSMUSG00000041138	10.808963	44.224384	4.755472e-25
38	ENSMUSG00000018102	8.117321	178.620010	1.201341e-13	ENSMUSG00000014498	8.617570	124.853401	3.713066e-15	ENSMUSG00000020358	7.918046	inf	1.309917e-12	ENSMUSG00000062054	4.726429	356.474304	5.259039e-04	ENSMUSG00000053012	10.549532	667.095886	2.771669e-23	ENSMUSG00000057054	8.378588	inf	1.219592e-14	ENSMUSG00000057054	9.610866	inf	1.111897e-19	ENSMUSG00000028367	6.210843	inf	1.312819e-07	ENSMUSG00000005672	8.348313	inf	3.759446e-14	ENSMUSG00000005566	7.654404	NaN	1.054413e-11	ENSMUSG00000074397	5.436067	300.242371	1.067903e-05	ENSMUSG00000038845	10.624108	NaN	1.249818e-23	ENSMUSG00000032733	8.025130	294.125763	4.569014e-13	ENSMUSG00000032852	10.792939	304.172455	5.581918e-25
39	ENSMUSG00000074637	8.075441	150.058151	1.655339e-13	ENSMUSG00000069273	8.592979	110.775238	4.485846e-15	ENSMUSG00000062444	7.906251	inf	1.404131e-12	ENSMUSG00000032657	4.704062	181.422836	5.625127e-04	ENSMUSG00000031715	10.541922	inf	2.930263e-23	ENSMUSG00000024155	8.377050	251.302048	1.222473e-14	ENSMUSG00000085840	9.598436	33.624336	1.236418e-19	ENSMUSG00000074578	6.192357	668.383118	1.399139e-07	ENSMUSG00000032249	8.303944	133.634857	5.331168e-14	ENSMUSG00000022474	7.622097	NaN	1.321193e-11	ENSMUSG00000039329	5.372164	NaN	1.390757e-05	ENSMUSG00000063524	10.597474	NaN	1.620541e-23	ENSMUSG00000098112	8.014524	513.933044	4.877294e-13	ENSMUSG00000015980	10.779205	405.565186	6.346268e-25
40	ENSMUSG00000039001	8.042783	inf	2.089343e-13	ENSMUSG00000021196	8.576842	640.355835	5.035946e-15	ENSMUSG00000027715	7.833958	inf	2.441455e-12	ENSMUSG00000051159	4.688323	77.850838	5.832453e-04	ENSMUSG00000030884	10.528224	inf	3.306810e-23	ENSMUSG00000032065	8.371287	269.899750	1.257033e-14	ENSMUSG00000054408	9.555412	484.545410	1.809976e-19	ENSMUSG00000104960	6.158553	171.430374	1.689607e-07	ENSMUSG00000020812	8.296021	285.214233	5.559838e-14	ENSMUSG00000028851	7.602215	NaN	1.503376e-11	ENSMUSG00000019139	5.360795	NaN	1.435661e-05	ENSMUSG00000040463	10.582635	NaN	1.823246e-23	ENSMUSG00000069049	7.996294	169.738083	5.540696e-13	ENSMUSG00000038393	10.768087	inf	7.062998e-25
41	ENSMUSG00000021411	7.992451	91.574432	2.948363e-13	ENSMUSG00000097772	8.545337	32.158131	6.461185e-15	ENSMUSG00000023004	7.822543	NaN	2.609787e-12	ENSMUSG00000022914	4.675897	inf	6.075526e-04	ENSMUSG00000061232	10.505014	inf	4.129459e-23	ENSMUSG00000002833	8.362066	inf	1.331569e-14	ENSMUSG00000029784	9.545214	274.806427	1.969860e-19	ENSMUSG00000025508	6.144292	NaN	1.790225e-07	ENSMUSG00000060206	8.286908	192.098740	5.859651e-14	ENSMUSG00000029249	7.555411	inf	2.105000e-11	ENSMUSG00000017764	5.355307	inf	1.453091e-05	ENSMUSG00000018326	10.581874	inf	1.823246e-23	ENSMUSG00000022849	7.985024	441.039581	5.949674e-13	ENSMUSG00000029322	10.721654	122.006172	1.144675e-24
42	ENSMUSG00000031523	7.963251	85.648529	3.658033e-13	ENSMUSG00000032515	8.537269	89.259338	6.657716e-15	ENSMUSG00000017861	7.810748	inf	2.799387e-12	ENSMUSG00000032431	4.655187	315.054504	6.527386e-04	ENSMUSG00000063480	10.498926	inf	4.302173e-23	ENSMUSG00000020419	8.337477	339.656342	1.591044e-14	ENSMUSG00000034723	9.522587	393.600372	2.416709e-19	ENSMUSG00000086290	6.091475	294.197784	2.277741e-07	ENSMUSG00000020402	8.276212	384.198639	6.261367e-14	ENSMUSG00000033751	7.546712	166.680008	2.198071e-11	ENSMUSG00000021848	5.354522	124.410980	1.453091e-05	ENSMUSG00000074397	10.520995	inf	3.404565e-23	ENSMUSG00000073460	7.969114	395.583954	6.635161e-13	ENSMUSG00000009941	10.691896	inf	1.547314e-24
43	ENSMUSG00000050856	7.926750	158.263229	4.716048e-13	ENSMUSG00000035203	8.536500	124.810936	6.657716e-15	ENSMUSG00000054405	7.773459	inf	3.675188e-12	ENSMUSG00000016637	4.601341	160.203964	7.729063e-04	ENSMUSG00000017707	10.491697	inf	4.538887e-23	ENSMUSG00000040841	8.329023	40.737133	1.675661e-14	ENSMUSG00000024155	9.485300	160.356232	3.434562e-19	ENSMUSG00000040952	6.077214	NaN	2.397540e-07	ENSMUSG00000045817	8.270666	105.442490	6.410567e-14	ENSMUSG00000036371	7.516476	NaN	2.707984e-11	ENSMUSG00000034341	5.323551	310.810059	1.651907e-05	ENSMUSG00000006998	10.507678	NaN	3.832028e-23	ENSMUSG00000000253	7.955525	272.290985	7.263240e-13	ENSMUSG00000044562	10.690262	262.991150	1.564542e-24
44	ENSMUSG00000020962	7.917529	inf	5.029395e-13	ENSMUSG00000005672	8.509989	inf	8.006979e-15	ENSMUSG00000034330	7.761283	inf	3.955965e-12	ENSMUSG00000041859	4.588915	NaN	8.102741e-04	ENSMUSG00000067702	10.444516	NaN	7.304814e-23	ENSMUSG00000067702	8.329023	NaN	1.675661e-14	ENSMUSG00000098358	9.468409	262.101990	4.010905e-19	ENSMUSG00000050856	6.059784	inf	2.600103e-07	ENSMUSG00000020186	8.266308	492.115753	6.501414e-14	ENSMUSG00000047945	7.494109	inf	3.121426e-11	ENSMUSG00000009894	5.302381	inf	1.779585e-05	ENSMUSG00000076617	10.465062	inf	5.881387e-23	ENSMUSG00000096255	7.945250	146.663925	7.742485e-13	ENSMUSG00000006457	10.652984	621.815491	2.248756e-24
45	ENSMUSG00000105039	7.900623	38.950268	5.667483e-13	ENSMUSG00000099517	8.505379	67.615089	8.154424e-15	ENSMUSG00000020592	7.706493	738.891907	5.952776e-12	ENSMUSG00000002416	4.584773	39.036774	8.102741e-04	ENSMUSG00000025630	10.435384	inf	7.762125e-23	ENSMUSG00000026277	8.318266	NaN	1.817296e-14	ENSMUSG00000052616	9.453749	240.039642	4.553914e-19	ENSMUSG00000071415	6.041297	NaN	2.890246e-07	ENSMUSG00000025967	8.258385	NaN	6.796706e-14	ENSMUSG00000040681	7.492038	NaN	3.121426e-11	ENSMUSG00000028378	5.289051	210.774719	1.886519e-05	ENSMUSG00000025393	10.455931	NaN	6.335664e-23	ENSMUSG00000058328	7.912105	136.457794	9.923300e-13	ENSMUSG00000025202	10.642193	173.063492	2.463111e-24
46	ENSMUSG00000058013	7.895628	308.003204	5.824983e-13	ENSMUSG00000015023	8.500000	81.550468	8.363354e-15	ENSMUSG00000018446	7.697742	NaN	6.239226e-12	ENSMUSG00000055817	4.549566	288.457764	9.254022e-04	ENSMUSG00000027722	10.434623	inf	7.762125e-23	ENSMUSG00000046338	8.263323	NaN	2.786526e-14	ENSMUSG00000071470	9.430484	425.172455	5.576280e-19	ENSMUSG00000060143	6.024396	NaN	3.149376e-07	ENSMUSG00000029094	8.247688	268.077942	7.275190e-14	ENSMUSG00000024217	7.488310	156.794952	3.143029e-11	ENSMUSG00000015869	5.276898	NaN	2.001462e-05	ENSMUSG00000028410	10.434623	NaN	7.692305e-23	ENSMUSG00000021179	7.858409	525.415283	1.396201e-12	ENSMUSG00000074665	10.623554	190.167221	2.936125e-24
47	ENSMUSG00000025362	7.876802	NaN	6.646391e-13	ENSMUSG00000020257	8.460810	239.072983	1.147405e-14	ENSMUSG00000070837	7.659692	285.264893	8.221657e-12	ENSMUSG00000020385	4.545010	196.358841	9.323482e-04	ENSMUSG00000055943	10.426252	inf	8.066317e-23	ENSMUSG00000029705	8.262938	353.626495	2.786526e-14	ENSMUSG00000038695	9.421880	392.144379	5.975719e-19	ENSMUSG00000046364	6.021755	NaN	3.149376e-07	ENSMUSG00000097772	8.222334	49.423809	8.803980e-14	ENSMUSG00000020027	7.482512	inf	3.216484e-11	ENSMUSG00000028525	5.225932	140.385574	2.446018e-05	ENSMUSG00000026234	10.433481	NaN	7.692305e-23	ENSMUSG00000036912	7.852112	626.760315	1.431318e-12	ENSMUSG00000054003	10.619957	inf	3.033326e-24
48	ENSMUSG00000091021	7.873728	31.908327	6.748745e-13	ENSMUSG00000036155	8.444288	69.887093	1.295346e-14	ENSMUSG00000021806	7.651321	inf	8.595978e-12	ENSMUSG00000079435	4.544595	NaN	9.323482e-04	ENSMUSG00000022174	10.425872	NaN	8.066317e-23	ENSMUSG00000051977	8.241423	700.015625	3.188751e-14	ENSMUSG00000000823	9.399570	405.061432	7.205221e-19	ENSMUSG00000022048	6.013832	391.824829	3.251249e-07	ENSMUSG00000024754	8.202526	443.248291	1.000111e-13	ENSMUSG00000047751	7.479198	NaN	3.231307e-11	ENSMUSG00000062444	5.160853	inf	3.233007e-05	ENSMUSG00000028691	10.426252	NaN	8.130995e-23	ENSMUSG00000022487	7.847471	593.196228	1.438109e-12	ENSMUSG00000036880	10.609493	inf	3.333429e-24
49	ENSMUSG00000030432	7.870270	NaN	6.874281e-13	ENSMUSG00000086290	8.441983	169.743683	1.295346e-14	ENSMUSG00000001525	7.617838	NaN	1.092408e-11	ENSMUSG00000031591	4.533412	262.582214	9.660941e-04	ENSMUSG00000026021	10.423969	inf	8.066317e-23	ENSMUSG00000038187	8.217985	inf	3.663352e-14	ENSMUSG00000062170	9.398296	578.268677	7.248019e-19	ENSMUSG00000032330	5.982670	NaN	3.772696e-07	ENSMUSG00000046434	8.202130	NaN	1.000111e-13	ENSMUSG00000028832	7.469671	inf	3.380111e-11	ENSMUSG00000046879	5.155365	180.239044	3.288309e-05	ENSMUSG00000021273	10.417120	inf	8.771522e-23	ENSMUSG00000019139	7.810349	NaN	1.857775e-12	ENSMUSG00000028150	10.502892	299.704712	9.673866e-24

DE_female_E105 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E10.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
DE_female_E115 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E11.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
DE_female_E125 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E12.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
DE_female_E135 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E13.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
DE_female_E145 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E14.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
DE_female_E155 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E15.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
DE_female_E165 = sc.get.rank_genes_groups_df(gcAnndata, group='female_E16.5', pval_cutoff=0.05, log2fc_min=1.588, key="rank_genes_groups", gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False])
sc.tl.rank_genes_groups(gcAnndata, groupby="stage_sex", groups=["female_E16.5"], reference = "female_E13.5", method='wilcoxon', tie_correct=True, key_added="female", pts=True)
DE_female_E165vE135 = sc.get.rank_genes_groups_df(gcAnndata, group="female_E16.5", key="female", pval_cutoff=0.05, log2fc_min=1.588, gene_symbols="external_gene_name")

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['female']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:00)

#DE_female_E165vE135 = sc.get.rank_genes_groups_df(gcAnndata,
#                                                  group="female_E16.5", 
#                                                  key="female",
#                                                  pval_cutoff=0.01, 
#                                                  log2fc_min=2,
#                                                  gene_symbols="external_gene_name").sort_values(by=["scores"], ascending=[False]).dropna(axis=0)#["external_gene_name"].to_list())
DE_female_E165vE135[DE_female_E165vE135.pvals_adj<0.05]

	names	scores	logfoldchanges	pvals	pvals_adj	external_gene_name	pct_nz_group
0	ENSMUSG00000031397	8.812840	inf	1.220150e-18	3.690778e-15	Tktl1	1.000000
1	ENSMUSG00000096210	8.531160	inf	1.448876e-17	2.788955e-14	H1f0	0.985915
2	ENSMUSG00000009596	8.432611	inf	3.380348e-17	4.771699e-14	Taf7l	1.000000
3	ENSMUSG00000051592	8.376738	763.262146	5.441513e-17	6.064137e-14	Ccnb3	0.957746
4	ENSMUSG00000031432	8.178836	inf	2.865999e-16	2.758394e-13	Prps1	0.943662
...	...	...	...	...	...	...	...
1646	ENSMUSG00000032913	2.639403	72.368431	8.305215e-03	4.984542e-02	Lrig2	0.788732
1647	ENSMUSG00000024521	2.638535	39.953098	8.326498e-03	4.995899e-02	Pmaip1	0.267606
1648	ENSMUSG00000026005	2.638428	49.923851	8.329134e-03	4.996064e-02	Rpe	0.605634
1649	ENSMUSG00000045382	-2.687850	2.531237	7.191361e-03	4.471949e-02	Cxcr4	0.070423
1650	ENSMUSG00000032702	-2.930349	6.624206	3.385819e-03	2.554019e-02	Kank1	0.309859

1651 rows × 7 columns

with pd.ExcelWriter('/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23/GermCell_DEresults_17Jul23.xlsx') as writer: DE_female_E105.to_excel(writer, sheet_name='E10.5_Female') DE_female_E115.to_excel(writer, sheet_name='E11.5_Female') DE_female_E125.to_excel(writer, sheet_name='E12.5_Female') DE_female_E135.to_excel(writer, sheet_name='E13.5_Female') DE_female_E145.to_excel(writer, sheet_name='E14.5_Female') DE_female_E155.to_excel(writer, sheet_name='E15.5_Female') DE_female_E165.to_excel(writer, sheet_name='E16.5_Female') DE_female_E165vE135.to_excel(writer, sheet_name='E16.5vE13.5_Female')

gcAnndata.write_h5ad("/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_17Jul23//gcAnndata_reproduce.h5ad")

sc.tl.rank_genes_groups(gcAnndata, 'stage_sex', method='wilcoxon')

ranking genes
WARNING: It seems you use rank_genes_groups on the raw count data. Please logarithmize your data before calling rank_genes_groups.
    finished: added to `.uns['rank_genes_groups']`
    'names', sorted np.recarray to be indexed by group ids
    'scores', sorted np.recarray to be indexed by group ids
    'logfoldchanges', sorted np.recarray to be indexed by group ids
    'pvals', sorted np.recarray to be indexed by group ids
    'pvals_adj', sorted np.recarray to be indexed by group ids (0:00:01)

sc.pl.rank_genes_groups(gcAnndata, n_genes=25, sharey=False, gene_symbols='external_gene_name',)

with pd.ExcelWriter('/users/k2142342/Lab_Sangrithi/working/Mahesh_Sangrithi/GermCell_SmartSeq2/FeatureCounts_OUT_9Feb23/GermCell_DEresults_9Feb23_bystagesex.xlsx') as writer: .to_excel(writer, sheet_name='Female') .to_excel(writer, sheet_name='Male')

#sc.get.rank_genes_groups_df(gcAnndata, group='male_E12.5', 
#                                        pval_cutoff=0.00001, 
#                                        log2fc_min=1.5,
#                                        gene_symbols="external_gene_name",
#                                        key="rank_genes_groups").sort_values(by=["scores"], 
#                                        ascending=[False]).dropna(axis=0)["external_gene_name"].to_list()

gslist = {}
for i in ['male_E10.5', 'female_E10.5', 'male_E11.5', 'female_E11.5', 'male_E12.5', 'female_E12.5', 'male_E13.5', 'female_E13.5', 'male_E14.5', 'female_E14.5', 'male_E15.5', 'female_E15.5', 'male_E16.5', 'female_E16.5']:
    genes = sc.get.rank_genes_groups_df(gcAnndata, 
                                        group = i, 
                                        pval_cutoff=0.01, 
                                        log2fc_min=2,
                                        gene_symbols="external_gene_name",
                                        key="rank_genes_groups").sort_values(by=["scores"], 
                                        ascending=[False]).dropna(axis=0)["external_gene_name"].to_list()
    gslist[i] = genes

top10 = pd.Series(gslist['male_E11.5'][:10] + gslist['male_E12.5'][:10] + gslist['male_E13.5'][:10] + gslist['male_E14.5'][:10] + gslist['male_E15.5'][:10] + gslist['male_E16.5'][:10] + gslist['female_E11.5'][:10] + gslist['female_E12.5'][:10] + gslist['female_E13.5'][:10] + gslist['female_E14.5'][:10] + gslist['female_E15.5'][:10] + gslist['female_E16.5'][:10], name = 'top10')
top10.drop_duplicates()

0              H4c14
1              Abhd2
2            Tbc1d13
3             H2ac15
4                Uty
           ...      
115            Ccnb3
116            Sycp1
117    1700029J07Rik
118            Sycp3
119             Aspa
Name: top10, Length: 110, dtype: object

sns.set_context("paper", font_scale=1, rc={"font.size":7,"axes.labelsize":7,"axes.titlesize":14})
d = sc.pl.matrixplot(gcAnndata,
                     top10.drop_duplicates(), 
                     cmap = 'Reds', 
                     groupby = "stage_sex", 
                     standard_scale="var", 
                     gene_symbols='external_gene_name', 
                     edgecolor="white", 
                     linewidths=-0,
                     #swap_axes = True, 
                     figsize = [11,2],
                     #save = "male_female_top10_horiz.pdf",
                     )